camGates and Hillman Centers Photo Tour
School of Computer Science, carnegie Mellon
Computer Science Department
Human-Computer Interaction Inst
Institute for Software Research
Lane Ctr for Computational Biology
Language Technologies Institute
Machine Learning Department
Robotics Institute
Entertainment Technology Center
Extended Menu Contact Info Directory About SCS SCS New Buildings Info Giving to SCS SCS Dean's Advisory Board

SCS DISTINGUISHED LECTURE SERIES
4:00 PM - Wean Hall 7500
3:45 PM Distinguished Donuts - Outside the Hall

Salim Roukos
Manager, Natural Language Technologies Department
IBM T.J. Watson Research Center

Translingual Information Processing

Searching unstructured information in the form of (largely) text with increasing image, audio and video content is fast becoming a daily activity for many people. Increasingly, the content is becoming multilingual (e.g. one such trend is that non-english speakers became the majority of online users in the summer of 2001 and continue to increase their share). To help assist users with accessing answers to their information needs regardless of the original language of the relevant content, we at IBM Research have a number of projects to handle multilingual content ranging from machine translation, information extraction, to topic detection and tracking. In this talk, we will present an overview of our work on statistical machine translation and demonstrate a cross-lingual search engine to search Arabic content using English queries. We will also briefly discuss an automated metric, called Bleu, for the evaluation of translation systems.

Speaker Bio:

Salim Roukos is the Manager of Natural Language Technologies Department at IBM T. J. Watson Research Center. The research groups in his department focus on various areas of statistical modeling for Natural Language Processing covering language modeling, parsing, natural language understanding for conversational systems, information extraction, and machine translation.

Dr. Roukos received his B.E. from the American University of Beirut, in 1976, his M.Sc. and Ph.D. from the University of Florida, in 1978 and 1980, respectively. He joined Bolt Beranek and Newman from 1980 through 1989, where he was a Senior Scientist in charge of projects in speech compression, time scale modification, speaker identification, word spotting, and spoken language understanding. He was an Adjunct Professor at Boston University in 1988 before joining IBM in 1989.

Dr. Roukos has served as Chair of the IEEE Digital Signal Processing Committee in 1988. He also has chaired and served on various committees sponsored by the Advanced Research Projects Agency on speech recognition and language understanding technologies. He is currrently Porgram co-chair of the HLT/NAACL 2004 conference to be held on May 2-7, 2004, Boston, MA.

<< Back