Speaker:Dr. Kevin Knight
Information Sciences Institute
University of Southern California
Time:9:30am--10:30am, Apr 1, 2009 (WED)
Place:Report Hall, 4th Floor, ICT

Abstract:
We study a number of natural language decipherment problems using unsupervised methods. These problems include letter substitution ciphers, character code conversion, archaeological phonetic decipherment, and word-based ciphers.  We aim at training statistical machine translation systems without parallel data, in which text in one language is viewed as a code for text in another language. In addition, we study Shannon's formulas concerning how much intercepted data is required to solve a given type of cipher.
 
Bio:
Dr. Kevin Knight is a Senior Research Scientist and Fellow at the Information Sciences Institute of the University of Southern California. He is a Research Associate Professor in the Computer Science Department at USC, and he is also Chief Scientist at Language Weaver, Inc.  Dr. Knight received his PhD from Carnegie Mellon University in 1991 and his BA from Harvard University in 1986. He is co-author, with Elaine Rich, of the textbook Artificial Intelligence.  His main research interests are statistical natural language processing, machine translation, natural language generation, and decipherment.  Dr. Knight has authored over fifty scientific papers on language translation, and he is active in building and deploying large-scale language translation systems.  Previously, he served on the editorial boards of the Computational Linguistics journal, the Journal of Artificial Intelligence Research, and the ACM Transactions on Speech and Language Processing.  Dr. Knight was general chair of the conference of the Association for Computational Linguistics (ACL) in 2005, and he was elected to serve as ACL president in 2011.