Computer Science
Trustworthy Information Retrieval
Abstract: Access to reliable information is essential. How do we ensure that the technology that we use to connect people to information is itself trustworthy? In the talk I decompose this question intrinsic aspects, having to do with transparency of information retrieval methods, and extrinsic aspects, having to do with robustness of information retrieval methods. The talk will be example-based in an attempt to make two key dimensions (transparency and robustness) as tangible as possible.
You may also join via the following Zoom: https://umd.zoom.us/j/98806584197?pwd=SXBWOHE1cU9adFFKUmN2UVlwUEJXdz09
Title and abstract TBA.
(Note that the time differs from regular colloquium time)
Towards Explainable Retrieval Models for Professional Search Tasks
"Think before you speak": Language Generation with Planning
**Please note that the time differs from the regular meeting time**
How children are and aren’t like adults when it comes to interpreting pronouns: A developmental modeling investigation
Towards Human-Centered AI: Understanding Human Production and Consumption of Explanations
Examining Racially Biased Language within a Large Corpus American Football Commentary
You are cordially invited to a virtual screening and panel discussion of the film
CODED BIAS
Movie Viewing: Wednesday, 3/24 - Monday, 3/29
Virtual Panel Discussion: Friday, 3/26 at 4 p.m.
Register to receive the viewing link and the panel discussion link.
ABOUT THE FILM:
Neural Information Retrieval: In search of meaningful progress
Nataliya Stepanova -- a Math and CS double degree student and Linguistics minor, and an alum of LSC’s PULSAR undergraduate research program -- has become the University’s sixth (ever) recipient of a Marshall Scholarship. Pandemic permitting, she will be heading to Scotland in the Fall to earn a Master’s in Speech and Language Processing at the University of Edinburgh.