<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
	<id>https://wiki.umiacs.umd.edu/clip/api.php?action=feedcontributions&amp;feedformat=atom&amp;user=Laplante</id>
	<title>CLIP - User contributions [en]</title>
	<link rel="self" type="application/atom+xml" href="https://wiki.umiacs.umd.edu/clip/api.php?action=feedcontributions&amp;feedformat=atom&amp;user=Laplante"/>
	<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php/Special:Contributions/Laplante"/>
	<updated>2026-04-18T15:00:20Z</updated>
	<subtitle>User contributions</subtitle>
	<generator>MediaWiki 1.43.7</generator>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=256</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=256"/>
		<updated>2010-09-01T19:53:52Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Disambiguation */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid machine translation, MT evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || paraphrasing, summarization, language understanding&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed NLP, paraphrasing &lt;br /&gt;
&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; |&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jklavans Judith Klavans] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Raul David Guerra&lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
* Philip Resnik and David Yarowsky, &amp;quot;[http://www.cs.jhu.edu/~yarowsky/pubs/nle00.ps Distinguishing Systems and Distinguishing Senses: New Evaluation Methods for Word Sense Disambiguation]&amp;quot;, Natural Language Engineering 5(2), pp. 113-133.&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=255</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=255"/>
		<updated>2010-09-01T19:53:14Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Faculty */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://lampsrv02.umiacs.umd.edu/projdb/person.php?id=2 David Doermann]&#039;&#039;&#039;: Senior Research Scientist&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jklavans/ Judith Klavans]&#039;&#039;&#039;: Visiting Senior Research Scientist&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Researchers and Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
* David Zajic&lt;br /&gt;
* Rebecca LaPlante&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Irene Eleta: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Beth Emmerling: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Raul David Guerra: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Jes Koepfler: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff: Master&#039;s student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~sayyadi/ Hassan Sayyadi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
* Ke Wu, Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
Olivia Buzek&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Jordan Boyd-Graber&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Chris Dyer (Carnegie Mellon University)&lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (West Point)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=254</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=254"/>
		<updated>2010-08-31T20:13:00Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Faculty */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://lampsrv02.umiacs.umd.edu/projdb/person.php?id=2 David Doermann]&#039;&#039;&#039;: Senior Research Scientist&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* Judith Klavans: Senior Research Scientist&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Researchers and Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
* David Zajic&lt;br /&gt;
* Rebecca LaPlante&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Irene Eleta: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Beth Emmerling: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Raul David Guerra: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Jes Koepfler: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff: Master&#039;s student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~sayyadi/ Hassan Sayyadi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
* Ke Wu, Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
Olivia Buzek&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Jordan Boyd-Graber&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Chris Dyer (Carnegie Mellon University)&lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (West Point)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=253</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=253"/>
		<updated>2010-08-31T20:12:04Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Researchers and Post-Docs */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://lampsrv02.umiacs.umd.edu/projdb/person.php?id=2 David Doermann]&#039;&#039;&#039;: Senior Research Scientist&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Researchers and Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
* David Zajic&lt;br /&gt;
* Rebecca LaPlante&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Irene Eleta: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Beth Emmerling: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Raul David Guerra: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Jes Koepfler: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff: Master&#039;s student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~sayyadi/ Hassan Sayyadi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
* Ke Wu, Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
Olivia Buzek&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Jordan Boyd-Graber&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Chris Dyer (Carnegie Mellon University)&lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (West Point)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=252</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=252"/>
		<updated>2010-08-31T20:11:53Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Faculty */ Added link for D. Doermann&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://lampsrv02.umiacs.umd.edu/projdb/person.php?id=2 David Doermann]&#039;&#039;&#039;: Senior Research Scientist&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Researchers and Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* Judith Klavans&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
* David Zajic&lt;br /&gt;
* Rebecca LaPlante&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Irene Eleta: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Beth Emmerling: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Raul David Guerra: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Jes Koepfler: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff: Master&#039;s student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~sayyadi/ Hassan Sayyadi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
* Ke Wu, Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
Olivia Buzek&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Jordan Boyd-Graber&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Chris Dyer (Carnegie Mellon University)&lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (West Point)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=251</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=251"/>
		<updated>2010-08-31T17:55:20Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Graduate Students */ added Guerra, Eleta, Emmerling, Koepfler&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* David Doermann&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Researchers and Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* Judith Klavans&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
* David Zajic&lt;br /&gt;
* Rebecca LaPlante&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Irene Eleta: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Beth Emmerling: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Raul David Guerra: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Jes Koepfler: Ph.D. student, iSchool&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff: Master&#039;s student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~sayyadi/ Hassan Sayyadi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
* Ke Wu, Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
Olivia Buzek&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Jordan Boyd-Graber&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Chris Dyer (Carnegie Mellon University)&lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (West Point)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=250</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=250"/>
		<updated>2010-08-31T17:52:57Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Disambiguation */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid machine translation, MT evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || paraphrasing, summarization, language understanding&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed NLP, paraphrasing &lt;br /&gt;
&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; |&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Raul David Guerra&lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
* Philip Resnik and David Yarowsky, &amp;quot;[http://www.cs.jhu.edu/~yarowsky/pubs/nle00.ps Distinguishing Systems and Distinguishing Senses: New Evaluation Methods for Word Sense Disambiguation]&amp;quot;, Natural Language Engineering 5(2), pp. 113-133.&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=249</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=249"/>
		<updated>2010-08-31T17:52:22Z</updated>

		<summary type="html">&lt;p&gt;Laplante: Added postdocs to disambiguation&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid machine translation, MT evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || paraphrasing, summarization, language understanding&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed NLP, paraphrasing &lt;br /&gt;
&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; |&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Raul David Guerra, Irene Eleta, Jes Koepfler, Beth Emmerling&lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
* Philip Resnik and David Yarowsky, &amp;quot;[http://www.cs.jhu.edu/~yarowsky/pubs/nle00.ps Distinguishing Systems and Distinguishing Senses: New Evaluation Methods for Word Sense Disambiguation]&amp;quot;, Natural Language Engineering 5(2), pp. 113-133.&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=248</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=248"/>
		<updated>2010-08-31T17:50:09Z</updated>

		<summary type="html">&lt;p&gt;Laplante: &lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid machine translation, MT evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || paraphrasing, summarization, language understanding&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed NLP, paraphrasing &lt;br /&gt;
&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; |&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
* Philip Resnik and David Yarowsky, &amp;quot;[http://www.cs.jhu.edu/~yarowsky/pubs/nle00.ps Distinguishing Systems and Distinguishing Senses: New Evaluation Methods for Word Sense Disambiguation]&amp;quot;, Natural Language Engineering 5(2), pp. 113-133.&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=247</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=247"/>
		<updated>2010-08-31T17:44:08Z</updated>

		<summary type="html">&lt;p&gt;Laplante: Added Resnik and Yarowsky article&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid machine translation, MT evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || paraphrasing, summarization, language understanding&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed NLP, paraphrasing &lt;br /&gt;
&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; |&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
* Philip Resnik and David Yarowsky, &amp;quot;Distinguishing Systems and Distinguishing Senses: New Evaluation Methods for Word Sense Disambiguation&amp;quot;, Natural Language Engineering 5(2), pp. 113-133. (accessible through Google Scholar)&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=246</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=246"/>
		<updated>2010-08-30T20:17:07Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Paraphrasing */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid machine translation, MT evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || paraphrasing, summarization, language understanding&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed NLP, paraphrasing &lt;br /&gt;
&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; |&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=245</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=245"/>
		<updated>2010-08-30T20:16:05Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Machine Translation and Paraphrasing */  Split MT and paraphrasing into two sections per B. Dorr&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid machine translation, MT evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || paraphrasing, summarization, language understanding&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed NLP, paraphrasing &lt;br /&gt;
&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; |&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=244</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=244"/>
		<updated>2010-08-30T19:52:51Z</updated>

		<summary type="html">&lt;p&gt;Laplante: Changed title of &amp;#039;post docs&amp;#039; to &amp;#039;researchers and postdocs&amp;#039; and added 3 researchers&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* David Doermann&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Researchers and Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* Judith Klavans&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
* David Zajic&lt;br /&gt;
* Rebecca LaPlante&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff: Master&#039;s student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~sayyadi/ Hassan Sayyadi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
* Ke Wu, Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
Olivia Buzek&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Jordan Boyd-Graber&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Chris Dyer (Carnegie Mellon University)&lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (West Point)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=243</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=243"/>
		<updated>2010-08-30T19:51:23Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Post-Docs */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* David Doermann&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* Judith Klavans&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Researchers and Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
* David Zajic&lt;br /&gt;
* Rebecca LaPlante&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff: Master&#039;s student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~sayyadi/ Hassan Sayyadi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
* Ke Wu, Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
Olivia Buzek&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Jordan Boyd-Graber&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Chris Dyer (Carnegie Mellon University)&lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (West Point)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=242</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=242"/>
		<updated>2010-08-30T19:42:46Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Text Summarization */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation and Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid MT, semantically-informed syntactic MT&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, paraphrase, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=241</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=241"/>
		<updated>2010-08-30T19:35:03Z</updated>

		<summary type="html">&lt;p&gt;Laplante: &lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation and Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid MT, semantically-informed syntactic MT&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, paraphrase, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| David Zajic || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=240</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=240"/>
		<updated>2010-08-30T19:33:34Z</updated>

		<summary type="html">&lt;p&gt;Laplante: added text summarization&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Bayesian Modeling==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~hal Hal Daume III] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Eric Hardisty, [http://umiacs.umd.edu/~ynhu/ Yuening Hu], Ke Zhai&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Bayesian modeling is a rigorous mathematical formalism that allows us to build systems that reflect our uncertainty about the world.  Applied to language, they allow us to build models that reflect the &amp;quot;latent&amp;quot; aspects of communication such as topic, part of speech, syntax, or sentiment.  Using posterior inference, we can use the models to discover the latent features that best explain observed language.&lt;br /&gt;
&lt;br /&gt;
In the CLIP lab, we are interested in &lt;br /&gt;
* building tools that make it easier for people to work with Bayesian models&lt;br /&gt;
* scaling inference for Bayesian models to the web scale&lt;br /&gt;
* understanding how humans interpret and understand the latent variables in Bayesian models&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/~hal/HBC/ Hierarchical Bayes Compiler]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/nips2009-rtl.pdf Reading Tea Leaves: How Humans Interpret Topic Models]&lt;br /&gt;
* [http://drum.lib.umd.edu/handle/1903/10058 Gibbs Sampling for the Uninitiated]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Machine Translation and Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid MT, semantically-informed syntactic MT&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, paraphrase, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Text Summarization ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || evaluation&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper David Zajic] || sentence compression, sentence selection&lt;br /&gt;
|-&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
Text Summarization is the creation of a short document to serve as a surrogate for a longer document.  The CLIP Laboratory&#039;s approach to summarization enhances the extractive method of selecting source document sentences for inclusion in a summary by using sentence compression to enlarge the pool of available sentences, and by combining fluent text with topic terms.  Our sentence compression technology has encompassed both statistical and linguistic methodologies.  We have developed an extrinsic evaluation measure for summarization, Relevance Prediction, which is grounded in a real-world task using summarized documents. The CLIP Laboratory, in collaboration with BBN, has been a regular participant in NIST&#039;s summarization evaluations (Document Understanding Conferences and Text Analysis Conferences), and has contributed summarization components to DARPA Translingual Information Detection, Extraction and Summarization (TIDES), Surprise Language Exercise (SLE), and Global Autonomous Language Exploitation (GALE) programs, and to the iOpener project.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Douglas W. Oard] || topical relation detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
| [http://terpconnect.umd.edu/~oard/ Douglas W. Oard] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~ewagner/ Earl Wagner] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | Lidan Wang, [http://terpconnect.umd.edu/~tanx/ Tan Xu] &lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Douglas W. Oard, &amp;quot;[http://terpconnect.umd.edu/~oard/pdf/elis09.pdf Multilingual Information Access],&amp;quot; in Encyclopedia of Library and Information Sciences, 3rd Ed., 2009.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg Jordan Boyd-Graber] || &lt;br /&gt;
|-&lt;br /&gt;
| Judith Klavans || &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
* [http://www.umiacs.umd.edu/~jbg/docs/jbg-EMNLP07.pdf A Topic Model for Word Sense Disambiguation]&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=209</id>
		<title>Research</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=Research&amp;diff=209"/>
		<updated>2010-08-27T18:04:51Z</updated>

		<summary type="html">&lt;p&gt;Laplante: &lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Machine Translation and Paraphrasing==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || interlingual and hybrid MT, semantically-informed syntactic MT&lt;br /&gt;
|-&lt;br /&gt;
| [http://umiacs.umd.edu/~mharper Mary Harper] || multilingual parsing, language modeling&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || linguistically informed translation modeling, paraphrase, crowdsourcing and translation&lt;br /&gt;
|-&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~vlad/ Vlad Eidelman]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The CLIP Laboratory&#039;s work in &amp;lt;b&amp;gt;machine translation&amp;lt;/b&amp;gt; continues the lab&#039;s long tradition of research in translation.  Like most of the field, we work within the framework of statistical MT, but with an emphasis on taking appropriate advantage of knowledge driven or linguistically informed model structures, features, and priors.   Some current areas of research include syntactically informed language models, linguistically informed translation model features, the use of unsupervised methods in translation modeling, exploitation of large scale &amp;quot;cloud computing&amp;quot; methods, and human-machine collaborative translation via crowdsourcing.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Paraphrase&amp;lt;/b&amp;gt;, the ability to express the same meaning in multiple ways, is an active area of research within the NLP community and here in the CLIP Laboratory.  Our work in paraphrase  includes the use of paraphrase in MT evaluation and parameter estimation, lattice and forest translation, and collaborative translation, as well as research on lexical and phrasal semantic similarity measures, meaning preservation in machine translation and summarization, and large-scale document similarity computation via cloud computing methods.   &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Summarization ==&lt;br /&gt;
&lt;br /&gt;
==Parsing and Tagging==&lt;br /&gt;
&lt;br /&gt;
==Computational Social Science==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber] || scientific literature analysis, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~bonnie Bonnie Dorr] || sentiment analysis, scientific literature analysis&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || social media&lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Doug Oard] || technological innovation&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid] || diffusion, prediction, event detection&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || sentiment, persuasion&lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~weinberg Amy Weinberg] || sentiment, persuasion&lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | [http://www.cs.umd.edu/~hardisty/ Eric Hardisty] [http://www.umiacs.umd.edu/~asayeed/ Asad Sayed] [http://www.cs.umd.edu/~sayyadi Hassan Sayyadi] [http://www.cs.umd.edu/~wsc Shanchan Wu]&lt;br /&gt;
|-&lt;br /&gt;
| colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Computational social science&amp;lt;/b&amp;gt; involves the use of computational methods and models to leverage [http://www.sciencemag.org/cgi/content/summary/323/5915/721 &amp;quot;the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors&amp;quot;].  Research in the CLIP Laboratory is at the forefront of this emerging area, and includes sentiment analysis (computational modeling and prediction of opinions, perspective, and other private states), automatic analysis and visualization of the scientific literature, modeling the diffusion of technological innovations, and modeling and prediction of social goals and actions such as persuasion.  &lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Greene and Resnik, NAACL 2009: [http://umiacs.umd.edu/~resnik/pubs/greene_resnik_naacl2009.pdf More Than Words: Syntactic Packaging and Implicit Sentiment]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Information Retrieval: From Tweets to Tomes ==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] || &lt;br /&gt;
|-&lt;br /&gt;
|  [http://www.umiacs.umd.edu/~oard/ Doug Oard] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
The goal of information retrieval is to help people find what they are looking for.  Information retrieval research in the CLIP lab focuses principally on retrieval based on the language contained in text, in speech, and in document images.  We work across a broad range of content types, from tweets to tomes, from talking to texting, and from Cebuano to Chinese.  Three perspectives inform our work: &lt;br /&gt;
* we integrate a broad range of computational linguistics techniques,&lt;br /&gt;
* we focus on scalable techniques that can accommodate very large collections&lt;br /&gt;
* we sometimes draw the boundaries of our “systems” very broadly to include both the automated tools that we create and the process by which users can best employ those tools. &lt;br /&gt;
&lt;br /&gt;
One example that illustrates these perspectives is our work with “cross-language information retrieval,” in which close coupling of machine translation and information retrieval techniques make it possible for people to find and use information written in languages that they can neither read nor write.  Another example is our work on the design and evaluation of “question answering” systems that can automatically find and present answers to complex questions, which serves as a bridge between our work on information retrieval and summarization.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* Publication 1&lt;br /&gt;
* Publication 2&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
==Disambiguation==&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;0&amp;quot; cellpadding=&amp;quot;5&amp;quot; cellspacing=&amp;quot;0&amp;quot; align=&amp;quot;center&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Faculty&amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
{| border=&amp;quot;0&amp;quot;&lt;br /&gt;
| Judith Klavans|| &lt;br /&gt;
|-&lt;br /&gt;
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] || &lt;br /&gt;
|}&lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Postdocs &amp;lt;/b&amp;gt;&lt;br /&gt;
| &lt;br /&gt;
|-&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey; border-right: 1px solid grey; background:#ffefef&amp;quot; | &amp;lt;b&amp;gt;Graduate Students &amp;lt;/b&amp;gt;&lt;br /&gt;
| style=&amp;quot;border-bottom: 3px solid grey;&amp;quot; | &lt;br /&gt;
|-&lt;br /&gt;
|  colspan=&amp;quot;3&amp;quot; align=&amp;quot;left&amp;quot; |&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Disambiguation &amp;lt;/b&amp;gt; is the process of determining the meaning or senses of a word in its context;  disambiguation remains one of the most challenging NLP problems since discovering word senses involves syntactic, semantic and pragmatic contextual inferencing, along with a rich knowledge base to base selection upon. For example, the word &amp;quot;wing&amp;quot; in the theater differs from airplanes, yet another sense for furniture (&amp;quot;wing chair&amp;quot;) applies to some usages.  Often disambiguation can be based on windows of two and three words, but usually involves larger computation.  Techniques for disambiguation range from the use of large scale thesaural resources (such as WordNet) to purely statistical methods.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;b&amp;gt;Representative Publications and Project Pages:&amp;lt;/b&amp;gt;&lt;br /&gt;
* [http://www.umiacs.umd.edu/research/t3/index.shtml T3: Text, Tags, Trust]&lt;br /&gt;
&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
	<entry>
		<id>https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=208</id>
		<title>People</title>
		<link rel="alternate" type="text/html" href="https://wiki.umiacs.umd.edu/clip/index.php?title=People&amp;diff=208"/>
		<updated>2010-08-27T17:33:11Z</updated>

		<summary type="html">&lt;p&gt;Laplante: /* Faculty */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Faculty ==&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jbg/  Jordan Boyd-Graber]&#039;&#039;&#039;: Assistant Professor, the iSchool&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hal/ Hal Daum&amp;amp;eacute; III]&#039;&#039;&#039;: Assistant Professor, Computer Science, Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* David Doermann&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~bonnie/ Bonnie J. Dorr]&#039;&#039;&#039;: Professor of Computer Science and UMIACS, Associate Dean of College of Computer, Mathematical and Physical Sciences and College of Chemical and Life Sciences&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://terpconnect.umd.edu/~mharper/ Mary Harper]&#039;&#039;&#039;: Affiliate Research Professor, Computer Science, Electrical and Computer Engineering, and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* Judith Klavans&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin]&#039;&#039;&#039;: Associate Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.glue.umd.edu/~oard/ Douglas W. Oard]&#039;&#039;&#039;: Professor, the iSchool and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~louiqa/ Louiqa Raschid]&#039;&#039;&#039;: Professor, Smith School of Business and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~resnik/ Philip Resnik]&#039;&#039;&#039;: Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~weinberg/ Amy Weinberg]&#039;&#039;&#039;: Associate Professor, Department of Linguistics and Institute for Advanced Computer Studies&lt;br /&gt;
&lt;br /&gt;
==Post-Docs==&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.umd.edu/~telsayed/ Tamer Elsayed]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~hendra/ Hendra Setiawan]&#039;&#039;&#039;&lt;br /&gt;
* &#039;&#039;&#039;[http://www.umiacs.umd.edu/~thor/ Andreas Thor]&#039;&#039;&#039; (visiting)&lt;br /&gt;
&lt;br /&gt;
==Graduate Students==&lt;br /&gt;
 	&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~arvind/ Arvind Agarwal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.ling.umd.edu/~redpony/ Chris Dyer]&#039;&#039;&#039;: Ph.D. student, Department of Linguistics&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.umiacs.umd.edu/~vlad/ Vladimir Eidelman]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Denis Filimonov&lt;br /&gt;
&lt;br /&gt;
* Sergei Golitsinski &lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~amitg/ Amit Goyal]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~hardisty/ Eric Hardisty]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Zhongqiang Huang&lt;br /&gt;
&lt;br /&gt;
* Yakov Kronrod&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~abhik/ Abhishek Kumar]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;[http://www.cs.utah.edu/~jags/ Jagadeesh Jagarlamudi]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* &#039;&#039;&#039;Jiarong Jiang&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Craig Murray&lt;br /&gt;
&lt;br /&gt;
* Brianna Satinoff&lt;br /&gt;
&lt;br /&gt;
* Asad Sayeed&lt;br /&gt;
&lt;br /&gt;
* Hassan Sayyadi&lt;br /&gt;
&lt;br /&gt;
* Michael Subotin&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~fture/ Ferhan Ture]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Lidan Wang&lt;br /&gt;
&lt;br /&gt;
*&#039;&#039;&#039;[http://www.cs.umd.edu/~wsc/ Shanchan Wu]&#039;&#039;&#039;: Ph.D. student, Department of Computer Science&lt;br /&gt;
&lt;br /&gt;
* Tan Xu&lt;br /&gt;
&lt;br /&gt;
==Undergraduate Students==&lt;br /&gt;
&lt;br /&gt;
== CLIP Alumni ==&lt;br /&gt;
===Researchers and postdocs===&lt;br /&gt;
&lt;br /&gt;
Mari Broman-Olsen&lt;br /&gt;
&lt;br /&gt;
David Chiang&lt;br /&gt;
&lt;br /&gt;
Rebecca Hwa&lt;br /&gt;
&lt;br /&gt;
Gina Levow&lt;br /&gt;
&lt;br /&gt;
Saif Mohammad&lt;br /&gt;
&lt;br /&gt;
Smaranda Muresan&lt;br /&gt;
&lt;br /&gt;
Carolyn Sheffield&lt;br /&gt;
&lt;br /&gt;
Maria Esther Vidal&lt;br /&gt;
&lt;br /&gt;
Vladimir Zadorozhny&lt;br /&gt;
&lt;br /&gt;
Daniel Zeman&lt;br /&gt;
&lt;br /&gt;
===Ph.d Students===&lt;br /&gt;
&lt;br /&gt;
David Alexander (BBN)&lt;br /&gt;
&lt;br /&gt;
Aitziber Atutxa (Univ of the Basque Country)&lt;br /&gt;
&lt;br /&gt;
Necip Fazil Ayan (SRI)&lt;br /&gt;
&lt;br /&gt;
Laura Bright &lt;br /&gt;
&lt;br /&gt;
Ya-Hui Chang (Associate Professor, National Taiwan Ocean University, Keelung, Taiwan) &lt;br /&gt;
&lt;br /&gt;
Clara Cabezas &lt;br /&gt;
&lt;br /&gt;
Waiyian Chong (Yuan)&lt;br /&gt;
&lt;br /&gt;
Dina Demner-Fushman (National Library of Medicine)&lt;br /&gt;
&lt;br /&gt;
Mona Diab (Columbia University) &lt;br /&gt;
&lt;br /&gt;
Rebecca Green (Library of Congress)&lt;br /&gt;
&lt;br /&gt;
Nizar Habash (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Darsana P. Josyula&lt;br /&gt;
&lt;br /&gt;
Maria Katsova (Microsoft Research) &lt;br /&gt;
&lt;br /&gt;
Ed Kenschaft&lt;br /&gt;
&lt;br /&gt;
Okan Kolak (Google)&lt;br /&gt;
&lt;br /&gt;
Grecia Lapizco&lt;br /&gt;
&lt;br /&gt;
Adam Woie-Jyh Lee (NIH)&lt;br /&gt;
&lt;br /&gt;
Adam Lopez (Edinburgh)&lt;br /&gt;
&lt;br /&gt;
Jun Luo &lt;br /&gt;
&lt;br /&gt;
Nitin Madnani (ETS)&lt;br /&gt;
&lt;br /&gt;
Yuval Marton (Columbia University)&lt;br /&gt;
&lt;br /&gt;
Joseph Naft&lt;br /&gt;
&lt;br /&gt;
Scott Olsson&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (UC Irvine)&lt;br /&gt;
&lt;br /&gt;
Stacy President Hobson (IBM Research)&lt;br /&gt;
&lt;br /&gt;
Alejandro Rodriguez&lt;br /&gt;
&lt;br /&gt;
Grazia Russo-Lassner&lt;br /&gt;
&lt;br /&gt;
Wade Shen (MIT Lincoln Labs) &lt;br /&gt;
&lt;br /&gt;
Aga Skotowski (BBN)&lt;br /&gt;
&lt;br /&gt;
Matthew Snover (CUNY)&lt;br /&gt;
&lt;br /&gt;
Calandra Tate (Westpoint)&lt;br /&gt;
&lt;br /&gt;
Scott Thomas (Navy Research Labs) &lt;br /&gt;
&lt;br /&gt;
Clare Voss (Army Research Labs) &lt;br /&gt;
&lt;br /&gt;
Nate Waisbrot &lt;br /&gt;
&lt;br /&gt;
Jianqiang Wang (State University of New York at Buffalo)&lt;br /&gt;
&lt;br /&gt;
Yao Wu (Microsoft)&lt;br /&gt;
&lt;br /&gt;
David Zajic (Univeristy of Maryland - CASL)&lt;br /&gt;
&lt;br /&gt;
===MS Students===&lt;br /&gt;
Jacob Devlin&lt;br /&gt;
===Undergraduate Students===&lt;br /&gt;
&lt;br /&gt;
Aaron Elkiss (PhD student, University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Ayelet Goldin&lt;br /&gt;
&lt;br /&gt;
Gregory Marton (PhD student, MIT --&amp;gt; Google)&lt;br /&gt;
&lt;br /&gt;
Jesse Metcalf-Burton (PhD from University of Michigan)&lt;br /&gt;
&lt;br /&gt;
Michael Wasser&lt;br /&gt;
&lt;br /&gt;
Eric Nichols (MS student, Nara Institute of Science and Technology, Japan)&lt;br /&gt;
&lt;br /&gt;
Andrew Fister &lt;br /&gt;
&lt;br /&gt;
Noah Smith (PhD from JHU --&amp;gt; assistant professor, CMU)&lt;br /&gt;
&lt;br /&gt;
Jessica Stevens (BBN)&lt;br /&gt;
&lt;br /&gt;
Lisa Pearl (PhD from UMD --&amp;gt; assistant professor, UC Irvine)&lt;/div&gt;</summary>
		<author><name>Laplante</name></author>
	</entry>
</feed>