Actions

Research: Difference between revisions

Computational Linguistics and Information Processing

Line 10: Line 10:
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] ||  
| [http://www.umiacs.umd.edu/~jimmylin Jimmy Lin] ||  
|-
|-
| [http://umiacs.umd.edu/~hal Hal Daume III] ||  
| [http://umiacs.umd.edu/~hal Hal Daumé III] || automated models; multilingual models; nonparametric methods
|-
|-
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] ||  
| [http://www.umiacs.umd.edu/~resnik/ Philip Resnik] ||  

Revision as of 22:15, 1 September 2010

Bayesian Modeling

Faculty
Jordan Boyd-Graber
Jimmy Lin
Hal Daumé III automated models; multilingual models; nonparametric methods
Philip Resnik
Postdocs
Graduate Students Eric Hardisty, Yuening Hu, Ke Zhai

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 "latent" 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.

In the CLIP lab, we are interested in

  • building tools that make it easier for people to work with Bayesian models
  • scaling inference for Bayesian models to the web scale
  • understanding how humans interpret and understand the latent variables in Bayesian models

Representative Publications and Project Pages:

Machine Translation

Faculty
Bonnie Dorr interlingual and hybrid machine translation, MT evaluation
Mary Harper multilingual parsing, language modeling
Philip Resnik linguistically informed translation modeling, crowdsourcing and translation
Hal Daumé III domain adaptation for translation; translation with linguistic universals
Postdocs
Graduate Students Vlad Eidelman

The CLIP Laboratory's work in machine translation continues the lab'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 "cloud computing" methods, and human-machine collaborative translation via crowdsourcing.

Representative Publications and Project Pages:

Paraphrasing

Faculty
Bonnie Dorr paraphrasing, summarization, language understanding
Philip Resnik linguistically informed NLP, paraphrasing
Postdocs
Graduate Students

Paraphrase, 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.

Text Summarization

Faculty
Bonnie Dorr evaluation
David Zajic sentence compression, sentence selection
Postdocs
Graduate Students

Text Summarization is the creation of a short document to serve as a surrogate for a longer document. The CLIP Laboratory'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'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.

Parsing and Tagging

Computational Social Science

Faculty
Jordan Boyd-Graber scientific literature analysis, persuasion
Bonnie Dorr sentiment analysis, scientific literature analysis
Jimmy Lin social media
Douglas W. Oard topical relation detection
Louiqa Raschid diffusion, prediction, event detection
Philip Resnik sentiment, persuasion
Amy Weinberg sentiment, persuasion
Postdocs
Graduate Students Eric Hardisty Asad Sayed Hassan Sayyadi Shanchan Wu

Computational social science involves the use of computational methods and models to leverage "the capacity to collect and analyze data at a scale that may reveal patterns of individual and group behaviors". 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.

Representative Publications and Project Pages:

Information Retrieval

Faculty
Jimmy Lin
Douglas W. Oard
Postdocs
Earl Wagner
Graduate Students Lidan Wang, Tan Xu

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:

  • we integrate a broad range of computational linguistics techniques,
  • we focus on scalable techniques that can accommodate very large collections
  • 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.

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.

Representative Publications and Project Pages:


Disambiguation

Faculty
Jordan Boyd-Graber
Judith Klavans
Philip Resnik
Postdocs
Graduate Students Raul David Guerra

Disambiguation 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 "wing" in the theater differs from airplanes, yet another sense for furniture ("wing chair") 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.

Representative Publications and Project Pages: