EECS Joint Colloquium Distinguished Lecture Series

Wednesday, October 27, 2004
Hewlett Packard Auditorium, 306 Soda Hall
4:00-5:00 p.m.

Professor Fernando Pereira

Andrew and Debra Rachleff Professor and
Chairman of the Department of Computer and Information Science
University of Pennsylvania


Linear Models for Structure Prediction




Over the last few years, several groups have been developing models and algorithms for learning to predict the structure of complex data, sequences in particular, that extend well-known linear classification models and algorithms, such as logistic regression, the perceptron algorithm, and support vector machines. These methods combine the advantages of discriminative learning with those of probabilistic generative models like HMMs and probabilistic context-free grammars. I introduce linear models for structure prediction and their simplest learning algorithms, and exemplify their benefits with applications to information extraction from biomedical text, dependency parsing of English and Czech, and gene finding.

Joint work with Koby Crammer, Ryan McDonald, Fei Sha (University of Pennsylvania), Hanna Wallach (Cambridge University), in collaboration with Andrew McCallum and his group at the University of Massachusetts and John Lafferty at CMU, funded by NSF (EIA 0205448, EIA 0205456, IIS 0428193) and DARPA (SRI contract NBCHD030010).


Fernando Pereira is the Andrew and Debra Rachleff Professor and chairman of the department of Computer and Information Science, University of Pennsylvania. He received a Ph.D. in Artificial Intelligence from the University of Edinburgh in 1982. Before joining Penn, he held industrial research and management positions at SRI International, at AT&T Labs, where he led the machine learning and information retrieval research department from September 1995 to April 2000, and at WhizBang Labs, a Web information extraction company. His main research interests are in machine-learnable models of language and other natural sequential data such as biological sequences. His work on finite-state models for speech and text processing is now in everyday industrial use. He has 80 research publications on computational linguistics, speech recognition, machine learning and logic programming, and several issued and pending patents on speech recognition, language processing, and human-computer interfaces. He was elected Fellow of the American Association for Artificial Intelligence in 1991 for his contributions to computational linguistics and logic programming, and he is a past president of the Association for Computational Linguistics.