Computing That Serves

Constrained Conditional Models: Learning and Inference in Natural Language Understanding


Thursday, March 12, 2009 - 12:00pm


Dan Roth
Professor, Department of Computer Science, University of Illinois at Urbana-Champaign

Making decisions in natural language understanding tasks often involves assigning values to sets of interdependent variables where an expressive dependency structure among these can influence, or even dictate, what assignments are possible.  Structured learning problems provide one such example, but we are interested in a broader setting where multiple models are involved and it may not be ideal, or possible, to learn them jointly.

I will present work on Constrained Conditional Models (CCMs), a framework that augments probabilistic models with declarative constraints as a way to support decisions in an expressive output space while maintaining modularity and tractability of training.  Examples will be drawn from natural language understanding tasks such as semantic role learning (determining who did what to whom when and where), information extraction, transliteration and textual entailment (determining whether one utterance is a likely consequence of another).


Dan Roth is a Professor in the Department of Computer Science and the Beckman Institute at the University of Illinois at Urbana-Champaign and a Willet Faculty Scholar of the College of Engineering. He is the director of the DHS Institute of Discrete Science Center for Multimodal Information Access & Synthesis (MIAS) and has faculty positions also at the Statistics and Linguistics Departments.

Roth has published broadly in machine learning, natural language processing, knowledge representation and reasoning and learning theory, and has developed advanced machine learning based tools for natural language applications that are being used widely by the research community, including an award winning Semantic Parser.  Prof. Roth has given keynote talks in major conferences, including AAAI, The Conference of the American Association Artificial Intelligence; ICMLA, The International Conference on Machine Learning and Applications; EMNLP, The Conference on Empirical Methods in Natural Language Processing, and ECML & PKDD, the European Conference on Machine Learning and the Principles and Practice of Knowledge Discovery in Databases. He has also presented several tutorials in universities and conferences including at ACL and the European ACL. Among his paper awards are the best paper award in IJCAI-99 and the 2001 AAAI Innovative Applications of AI Award. Roth was the program chair of CoNLL'02 and of ACL'03, and has been on the editorial board of several journals in his research areas. He is currently an associate editor for the Journal of Artificial Intelligence Research and the Machine Learning Journal.  Prof. Roth got his B.A Summa cum laude in Mathematics from the Technion, Israel and his Ph.D in Computer Science from Harvard University in 1995.