Kevin Knight

University of Southern California

Sixty Years of Statistical Machine Translation


Automatic language translation (e.g., from Chinese to English) has long been a challenge for computer science.  I will describe some of the major results of statistical machine translation research since 1948.  Part of the talk will cover the explosion of work in the past few years that has resulted from intense interest on the part of scientists, funders, and industry.  I will also examine the roots of statistical translation in World War II decipherment activities.  Some of the concepts from that era have become core to the field, while others still remain to be picked up.




Kevin Knight is a Senior Research Scientist and Fellow at the Information Sciences Institute (ISI), and a Research Associate Professor in the Computer Science Department at the University of Southern California (USC).  Dr. Knight received a Ph.D. in computer science from Carnegie Mellon University in 1992 and a B.A. at Harvard University in 1986.  His research interests include artificial intelligence, natural language processing, statistical modeling, machine translation, and decipherment.  He served on the editorial boards of the Computational Linguistics journal and the Journal of Artificial Intelligence Research, and he was on the founding board of the journal ACM Transactions on Speech and Language Processing.  In 2005, he served as General Chair of the Annual Meeting of the Association for Computational Linguistics (ACL).  He was recently elected to serve as ACL Vice-president-elect in 2009, serving as President in 2011.   In addition, Dr. Knight is the Chief Scientist at Language Weaver, Inc., and the co-author (with Elaine Rich) of the textbook Artificial Intelligence.


B17 Upson Hall

Thursday, February 5, 2009

Refreshments at 3:45pm in the Upson 4th Floor Atrium

Computer Science

& Information Science


Spring 2009