Actions

Research: Difference between revisions

Computational Linguistics and Information Processing

Line 13: Line 13:
! colspan="3" style="border-bottom: 3px solid grey; background: #ffefef;" | <big>Cross‐language Bayesian models for Web‐scale text analysis using MapReduce </big>
! colspan="3" style="border-bottom: 3px solid grey; background: #ffefef;" | <big>Cross‐language Bayesian models for Web‐scale text analysis using MapReduce </big>
|-
|-
| style="border-right: 1px solid grey; background:#ffefef" | <b>PI</b>
| style="border-right: 1px solid grey; background:#ffefef" | <b>Faculty</b>
| [http://www.umiacs.umd.edu/~jbg/ Jimmy Lin]
| [http://www.umiacs.umd.edu/~jimmylin/ Jimmy Lin] [http://www.umiacs.umd.edu/~oard/ Doug Oard]
|-
|-
| style="border-right: 1px solid grey; background:#ffefef" | <b>Other Faculty </b>
| style="border-right: 1px solid grey; background:#ffefef" | <b>Postdocs </b>
| [http://www.umiacs.umd.edu/~jbg/ Jordan Boyd-Graber], [http://www.umiacs.umd.edu/~resnik/ Philip Resnik]
|  
|-
|-
| style="border-right: 1px solid grey; background:#ffefef" | <b>Graduate Students </b>
| style="border-right: 1px solid grey; background:#ffefef" | <b>Graduate Students </b>
Line 26: Line 26:
|-
|-
| style="border-bottom: 3px solid grey;" colspan="3" align="left" |
| style="border-bottom: 3px solid grey;" colspan="3" align="left" |


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:  
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:  
Line 35: Line 34:
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.
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.


|-
<b>Representative Publications:</b>
| style="background: #ffefef;" | Project Webpages
* Publication 1
| style="background: #ffefef;" | Example Publications
* Publication 2
| -
| Webpage
| Publication Title
|-


|}
|}

Revision as of 01:35, 13 August 2010

Machine Translation

Summarization

Parsing and Tagging

Sentiment Analysis

Information Retrieval: From Tweets to Tomes

Cross‐language Bayesian models for Web‐scale text analysis using MapReduce
Faculty Jimmy Lin Doug Oard
Postdocs
Graduate Students
Funding National Science Foundation 1018625

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:

  • Publication 1
  • Publication 2