NESCAI08: The Third North East Student Colloquium on Artificial Intelligence

2-4 May 2008, Ithaca, NY

Invited Talks

Lillian Lee

Only connect! Explorations in graph-based approaches to information retrieval and natural-language processing

Can we create a system that can learn to understand political speeches well enough to determine the speakers' viewpoints? Can we improve information retrieval by using link analysis, as is famously done in Web search, if we are dealing with documents that don't contain hyperlinks? And how can these two questions form the basis of a coherent talk? Answer: graphs!
Lillian Lee is an associate professor in the Computer Science Department of Cornell University. She is the recipient of the Best Paper Award at HLT-NAACL 2004 (joint with Regina Barzilay), a citation in "Top Picks: Technology Research Advances of 2004" by Technology Research News, and an Alfred P. Sloan Foundation Fellowship. But she is not from Iowa; nor is she ranked 843; and she is certainly not the pine-scented air.

Ben Taskar

Powers of Two: Alignment and Agreement between Models and Modalities

Problems of alignment or correspondence of different types of objects are predominant in many fields: phrase alignment for machine translation, matching of images/video and text, etc. In these tasks, the similarity between two corresponding elements is difficult to specify and tune by hand, since it involves elements of different types: words of different languages, faces and names, image regions and words. I will describe approaches to supervised and weakly supervised alignment learning that exploit the power of agreement between two models or two modalities.
Ben Taskar received his bachelor's and doctoral degree in Computer Science from Stanford University. After a postdoc at the University of California at Berkeley, he joined the faculty at the University of Pennsylvania Computer and Information Science Department in 2007. His research interests include machine learning, graphical models, large-scale and distributed convex optimization, applications in natural language processing, computer vision, and computational biology. His work on structured prediction has received awards at NIPS and EMNLP conferences.