Mitchell P. Marcus

RCA Professor of Artificial Intelligence	Office Address: Dept. of Computer & Information Science University of Pennsylvania 3330 Walnut Street 503 Levine Hall Philadelphia, PA 19104-6389 Email: mitch@cis.upenn.edu Tel: (215) 898-2538 FAX: (215) 898-0587

Research interests include: statistical and symbolic methods for automatic acquisition of linguistic structure; methodologies for annotation of linguistic structure in large text corpora; natural language processing; and cognitive science.

I Studied Linguistics and Applied Mathematics at Harvard University as an undergraduate (Magna cum Laude), and received a Ph.D. in Electrical Engineering and Computer Science in 1978 from MIT. From 1979-1987, I was a Member of Technical Staff at AT&T Bell Laboratories. At Penn, I hold the position of RCA Professor of Artificial Intelligence and was Chair of the Department of Computer and Information Science from 1994 to 2001. I also hold an appointment in Linguistics. I am currently (2002-2003) Chair of the Penn Faculty Senate. I was the principal investigator for the Penn Treebank Project through the mid-1990s, was President of the Association for Computational Linguistics in 1997, and have been a Fellow of the American Association of Artificial Intelligence since 1992. In 2002, I was the Chair of the 2nd Human Language Technologies Conference.

``Text Chunking using Transformation-Based Learning'', Association for Computational Linguistics Workshop on Very Large Corpora, Boston, MA, June 1995 (with Lance Ramshaw). Reprinted in Natural Language Processing Using Very Large Corpora, Armstrong et al. (eds.), Kluwer, 1998.

``New Trends in Natural Language Processing: Statistical Natural Language Processing'', Proceedings of the National Academy of Science, Vol 92, pp. 10052-10059, 1995. Reprinted in Voice Communication Between Humans and Machines, Rowe and Wilpon (eds.), National Academy Press, 1994.

``Building a large annotated corpus of English: the Penn Treebank.'' Computational Linguistics, Vol.19, 1993. Reprinted in Using Large Corpora, S. Armstrong (ed.), MIT Press, 1994. (with Beatrice Santorini and Mary Ann Marcinkiewicz)

``The Penn Treebank: A Revised Corpus Design for Extracting Predicate Argument Structure,'' 1994 ARPA Human Language Technology Workshop, Princeton, NJ, March 1994, Morgan-Kaufman (with 6 others).

A Theory of Syntactic Recognition for Natural Language, MIT Press, 1980.