Actions

Main Page: Difference between revisions

Computational Linguistics and Information Processing

Line 1: Line 1:
==Computational Linguistics and Information Processing at Maryland==
==Computational Linguistics and Information Processing at Maryland==


The CLIP laboratory at Maryland is engaged in designing algorithms and building systems which allow computers to effectively and efficiently perform human language-related tasks. The lab is a part of the <span class="plainlinks">'''[http://umiacs.umd.edu/ University of Maryland Institute for Advanced Computer Studies (UMIACS)]'''</span>, and is composed of faculty, researchers, and students spanning multiple departments, including the <span class="plainlinks">'''[http://www.cs.umd.edu/ Department of Computer Science]'''</span>,<span class="plainlinks"> '''[http://www.ling.umd.edu/ Department of Linguistics]'''</span>, <span class="plainlinks">'''[http://ischool.umd.edu/ iSchool]'''</span>, and the <span class="plainlinks">'''[http://www.rhsmith.umd.edu/ Robert H. Smith School of Business]'''</span>.  
The CLIP laboratory at Maryland is engaged in designing algorithms and building systems which allow computers to effectively and efficiently perform human language-related tasks. The lab is a part of the <span class="plainlinks">'''[http://umiacs.umd.edu/ University of Maryland Institute for Advanced Computer Studies (UMIACS)]'''</span>, and is composed of faculty, researchers, and students spanning multiple departments, including the <span class="plainlinks">'''[http://www.cs.umd.edu/ Department of Computer Science]'''</span>,<span class="plainlinks"> '''[http://www.ling.umd.edu/ Department of Linguistics]'''</span>, <span class="plainlinks">'''[http://ischool.umd.edu/ the iSchool]'''</span>, and the <span class="plainlinks">'''[http://www.rhsmith.umd.edu/ Robert H. Smith School of Business]'''</span>.  


CLIP consists of two main entities: The Natural Language Group and the Database Group. The natural language group focuses on several areas of broadscale multilingual processing, e.g., [[Research#Machine_Translation|machine translation]], [[Research#Summarization|summarization]], scalable translingual document detection, and cross-language information retrieval. The database group focuses on architectures for wide area computation with heterogeneous information servers, e.g., scientific discovery from biomolecular data sources. Several language researchers in the CLIP lab are also affiliated with the <span class="plainlinks">'''[http://lamp.cfar.umd.edu/media.htm Language and Media Processing (LAMP) Laboratory]'''</span>.
The group’s research covers most of the major areas of language research, including but not limited to speech recognition, handwriting and optical character recognition, multilingual text processing such as machine translation, and language data exploitation applications including document summarization, sense-making across structured data such as ontologies and thesauri, information retrieval, ranking and personalization, and sentiment analysis.
 
Natural language research focuses on several areas of broadscale multilingual processing, e.g., [[Research#Machine_Translation|machine translation]], [[Research#Summarization|summarization]], scalable translingual document detection, and cross-language information retrieval.  
 
Research in machine learning focuses on ...
 
Data management research focuses on architectures for wide area computation with heterogeneous information servers, pattern  discovery from the annotated hyperlinked Web of life science resources, personalization and ranking and recommendation for social media, and event detection and monitoring.
 
Several language researchers in the CLIP lab are also affiliated with the <span class="plainlinks">'''[http://lamp.cfar.umd.edu/media.htm Language and Media Processing (LAMP) Laboratory]'''</span>.


If you're interested in learning more, check out our <span class="plainlinks"> '''[http://clipsrv01.umiacs.umd.edu/wiki_pubs/ClipMedia.php Publications]'''</span>, or consider one of our [[Teaching|courses]]
If you're interested in learning more, check out our <span class="plainlinks"> '''[http://clipsrv01.umiacs.umd.edu/wiki_pubs/ClipMedia.php Publications]'''</span>, or consider one of our [[Teaching|courses]]

Revision as of 01:26, 11 June 2010

Computational Linguistics and Information Processing at Maryland

The CLIP laboratory at Maryland is engaged in designing algorithms and building systems which allow computers to effectively and efficiently perform human language-related tasks. The lab is a part of the University of Maryland Institute for Advanced Computer Studies (UMIACS), and is composed of faculty, researchers, and students spanning multiple departments, including the Department of Computer Science, Department of Linguistics, the iSchool, and the Robert H. Smith School of Business.

The group’s research covers most of the major areas of language research, including but not limited to speech recognition, handwriting and optical character recognition, multilingual text processing such as machine translation, and language data exploitation applications including document summarization, sense-making across structured data such as ontologies and thesauri, information retrieval, ranking and personalization, and sentiment analysis.

Natural language research focuses on several areas of broadscale multilingual processing, e.g., machine translation, summarization, scalable translingual document detection, and cross-language information retrieval.

Research in machine learning focuses on ...

Data management research focuses on architectures for wide area computation with heterogeneous information servers, pattern discovery from the annotated hyperlinked Web of life science resources, personalization and ranking and recommendation for social media, and event detection and monitoring.

Several language researchers in the CLIP lab are also affiliated with the Language and Media Processing (LAMP) Laboratory.

If you're interested in learning more, check out our Publications, or consider one of our courses