Applied Research on Question Answering at Microsoft
T. J. Hazen
, MSR Montreal
Date: Tuesday, April 30, 2019
Time: 4:00 PM to 5:00 PM
Location: 32-G882 (Stata Center, 8th Floor Hewlett Room)
Event Type: Seminar
Host: Jim Glass, MIT CSAIL
Contact: Marcia G. Davidson, 617-253-3049, email@example.com
Speaker URL: None
TALK: Applied Research on Question Answering at Microsoft
This talk will focus on our R&D efforts in question answering designed to solve problems that currently hinder the technology when deployed in real world applications and settings. The talk will provide a general overview of our question answering research and then discuss three specific problems our research is addressing: (1) how do you adapt question answering systems based on deep neural networks to new specialized domains using only limited amounts of in-domain data, (2) how do you select the highest quality, most convincing answer to show when multiple relevant answers are found, and (3) when extracting answers from documents retrieved from the internet how can you avoid showing inappropriate answers.
T. J. Hazen is a Principal Research Manager in Microsoft Research. Prior to joining MSR, T. J. previously served as a Principal Data Science Manager within Microsoft's Cloud AI and Bing groups where he led teams developing natural language processing and image processing components for Microsoft products. Before joining Microsoft in 2013, T. J. spent six years as a member of the Human Language Technology Group at MIT Lincoln Laboratory and nine years as a Research Scientist at the MIT Computer Science and Artificial Intelligence Laboratory. T. J. holds S.B., S.M., and Ph.D. degrees in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology.
Created by Marcia G. Davidson at Friday, April 26, 2019 at 5:09 PM.