Events & News
CS Colloquium
| Category | Lecture |
| Date | Wednesday, February 17, 2016 |
| Time | 11:00 am |
| Concludes | 12:15 pm |
| Location | Gould-Simpson 701 |
| Details | Please join us for coffee and light refreshments at 10:45am, Gould-Simpson, Rm 701 Faculty Host: Mihai Surdeanu |
| Speaker | Peter Clark |
| Title | Senior Research Manager |
| Affiliation | Allen Institute for Artificial Intelligence |
From Information Retrieval towards Knowledgeable Machines
At some point in the future, we will have knowledgeable machines - machines that contain internal models of the world and can answer questions, explain those answers, and dialog about them. A substantial amount of that knowledge will likely be extracted from text and assembled into internal representations that capture generalizations about the domain, and support explainable question-answering. At the Allen Institute for Artificial Intelligence (AI2), we are pursuing this goal with a medium-term focus on having the computer pass elementary science exams. In this presentation I will describe our research, in particular our work on acquiring simple, semi-structured representations from text and applying them to answer questions, including questions beyond the scope of information retrieval.
Biography
Peter Clark is a Senior Research Manager for AI2. His work focuses upon natural language processing, machine reasoning, large knowledge bases, and the interplay between these three areas. He has researched these topics for 30 years with more than 80 refereed publications and over 6000 citations.