View Seminar Video
Abstract
The Information Extraction (IE) task has driven a substantial body of natural language processing research during the past decade. We begin by presenting an overview of IE, including a description of the class of problems IE addresses, the manner in which IE systems are generally evaluated, and a typical IE system architecture. After a brief overview of previous work in applying machine learning techniques to IE problems, we describe some ambitious (and largely unsuccessful) attempts to learn discourse interpretation strategies within such a system. The results of this work led to a re-examination of the evaluation metrics used to drive the learning process, which has revealed some unforeseen attributes that should be avoided in future evaluation schemes.
Biography
Andrew Kehler received his Ph.D. in Computer Science from Harvard University in 1995, and is currently Senior Computer Scientist in the Artificial Intelligence Center at SRI International. His computational linguistics research has focused primarily on applying machine learning techniques to discourse interpretation problems in naturally-occurring data. His linguistic research has also centered on discourse processing, addressing problems in ellipsis, reference, and coherence resolution. In March, 2000, he will join the linguistics faculty at the University of California San Diego.