Speaker: Steven Bethard, School of Information, University of Arizona
Presentation Title: Parsing the Language of Time
Abstract: Getting a computer to understand the timeline underlying a written narrative is a critical component of tools for review of patient medical histories, analysis of intelligence reports, and tests of reading comprehension. But human language is rarely explicit in the way that would be most convenient for a computer, and events, times, and temporal relations are often implicit, left to be inferred by the reader. In this talk, I will first present a typical computational methodology for constructing timelines from the explicit and implicit cues of language: a series of supervised machine learning components trained on example texts whose timelines have been annotated manually by humans. Then I will show how we can improve this approach by analyzing big data that has not been annotated by humans but nonetheless reveals patterns in how humans talk about time. Finally, I will present an alternative approach to inferring timelines from text that achieves better generalization through modeling the incremental and compositional nature of the language of time.
Bio: Steven bethard is an Assistant Professor at the University of Arizona School of Information, where he co-directs the Computational Language Understanding Lab (CLU Lab). His research and teaching lie in the areas of machine learning and natural language processing. He was previously an assistant professor in Computer and Information Science at the University of Alabama at Birmingham and before that, worked as a postdoctoral researcher at Stanford University's Natural Language Processing group, Johns Hopkins University's Human Language Technology Center of Excellence, KULeuven's Language Intelligence and Information Retrieval group in Belgium, and the University of Colorado Boulder's Center for Language and Education Research. He received his Ph.D. in Computer Science and Cognitive Science from the University of Colorado Boulder in 2007.