Terri Griffith, Keith Beedie Chair in Innovation and Entrepreneurship, Simon Fraser University; 2022 ISSIP…
ISSIP Cognitive Systems Institute Group Speaker Series : September 13, 10:30am US Eastern Time
Engineered AI Still Matters for Question Answering
J. William Murdock, IBM
When: Thursday, September 13, 10:30 am US Eastern.
Zoom Detail Below
Background:
J. William Murdock is a researcher at IBM’s Watson Research Center and a development manager for the IBM Watson Discovery product. In 2001, he received a Ph.D. in Computer Science from Georgia Tech, where he was a member of Ashok Goel’s Design & Intelligence Laboratory. He worked as a post-doc with David Aha at the United States Naval Research Laboratory. Dr. Murdock has been working on the IBM Watson question answering system since the project began in 2007. He was the guest editor of the 2012 special issue of the IBM Journal of Research and Development entitled “This is Watson.” His research interests include question answering, natural-language semantics, analogical reasoning, knowledge-based planning, machine learning, and self-aware artificial intelligence.
Many question-answering systems rely on a significant amount of engineering effort. They often require both knowledge bases and rules, which can be very expensive to create. Even when there is significant statistical machine learning involved in these systems, there is also an enormous amount of effort spent on identifying what features are useful for the machine learning and implementing capabilities (often using knowledge bases and rules) to assign values to those features. However, in recent years an alternative approach has been growing in popularity: single-strategy systems in which one statistical model is used to address the entire task. In this presentation, William will describe work in which we pursue both approaches and also integrate the two together. He describes results across two different data sets and show that purely statistical approaches are an excellent fit for some data, but that engineered knowledge and rules remain useful for more realistic and open-ended tasks. For additional details, see his paper at http://www.cogsys.org/
Zoom meeting Link: https://zoom.us/j/7371462221
Zoom Callin: (415) 762-9988 or (646) 568-7788 Meeting id 7371462221
Zoom International Numbers: https://zoom.us/zoomconference
Check the website in case the date or time changes: http://cognitive-science.info/
Please retweet https://twitter.com/sumalaika/status/1039206952994316289
Join LinkedIn Group https://www.linkedin.com/