Main Page

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 and is part of the broader language science initiative at Maryland. 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:

• Department of Computer Science
• Department of Linguistics
• the iSchool
• 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 latent variable models of language, approximate inference, and how to make probabilistic models understandable to users.

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.