Faculty Host: Tina Eliassi-Rad
Abstract: In 2011, IBM's Watson system famously defeated the two best human players, Ken Jennings and Brad Rutter, in a two-game Jeopardy! exhibition match. The Watson Jeopardy! system demonstrated both high accuracy and speed in open-domain question answering that is unparalleled then and now. It achieved this level of performance through seamless integration of state-of-the-art techniques in Natural Language Processing, Information Retrieval, Knowledge Representation and Reasoning, Machine Learning, and High-Performance Computing.
Since 2011, the IBM Watson Research team has been working on developing rapid domain adaptation techniques to enable applications of Watson technologies in a variety of business domains.
In this talk, I will review the Watson Jeopardy! QA system and discuss the challenges we encountered during Watson adaptation process. I will also present some ongoing work that addresses them.
Bio: James Fan is a Research Staff Member at IBM Research Watson Group in Yorktown Heights, NY. His research interests include question answering, natural language processing, machine learning and knowledge representation & reasoning. James is an original team member and a technical lead of the Watson QA project which is advancing the state-of-the-art in automatic, open domain question answering technology. He has been working in the area of question answering since 2003, and has published over 40 peer reviewed papers (including a best paper award at International Semantic Web Conference in 2011) in leading AI journals and conferences. James also holds 15 US patents. Prior to joining IBM, James received his PhD at the University of Texas at Austin.
Suggested Readings: