[Colloquium] TOMORROW: Jordan Boyd-Graber (Maryland) – If We Want AI to be Interpretable, We Need to Define and Measure It

[Rob Mitchum]

*Part of the Computer Science/Statistics/Data Science Institute
Distinguished Speaker Series
<https://datascience.uchicago.edu/news/autumn-2022-distinguished-speaker-series/>*

*Friday, November 11th*
*12:00pm - 1:30pm (12:00 lunch, 12:30 talk)*
*In Person: John Crerar Library 390*
*Zoom: *
*https://uchicagogroup.zoom.us/j/92640945282?pwd=YkVlNGJteGhYWmUzOHBaZHJ5M2J4QT09*
<https://www.google.com/url?q=https://uchicagogroup.zoom.us/j/92640945282?pwd%3DYkVlNGJteGhYWmUzOHBaZHJ5M2J4QT09&sa=D&source=calendar&ust=1668522878595504&usg=AOvVaw1deLog1zd2VhmFMK7UrUJE>
*Meeting ID: *926 4094 5282
*Passcode: *761404

*Jordan Boyd-Graber*
*Associate Professor, Computer Science*
*University of Maryland*


*If We Want AI to be Interpretable, We Need to Define and Measure It*

*Abstract*: AI tools are ubiquitous, but most users treat it as a black
box: a handy tool that suggests purchases, flags spam, or autocompletes
text. While researchers have presented explanations for making AI less of a
black box, a lack of metrics make it hard to optimize explicitly for
interpretability. Thus, I propose two metrics for interpretability suitable
for unsupervised and supervised AI methods. For unsupervised topic models,
I discuss our proposed “intruder” interpretability metric, how it
contradicts the previous evaluation metric for topic models (perplexity),
and discuss its uptake in the community over the last decade. For
supervised question answering approaches, I show how human-computer
cooperation can be measured and directly optimized by a multi-armed bandit
approach to learn what kinds of explanations help specific users. I will
then briefly discuss how similar setups can help users navigate
information-rich domains like fact checking, translation, and web search.

*Bio*: Jordan Boyd-Graber <http://users.umiacs.umd.edu/~jbg/>’s research
focus is in applying machine learning to problems that help computers
better work with or understand humans. His research applies statistical
models to natural language problems in ways that interact with humans,
learn from humans, or help researchers understand humans. Jordan is an
expert in the application of topic models, automatic tools that discover
structure and meaning in large, multilingual datasets. His work has been
supported by NSF, DARPA, IARPA, and ARL. Three of his students have gone on
to tenure track positions at NYU, U Mass Amherst, and Ursinus. His awards
include a 2017 NSF CAREER, the Karen Spärk Jones prize; “best of” awards at
NIPS, CoNLL, and NAACL; and a Computing Innovation Fellowship (declined).
His Erdös number is 2 (via Maria Klawe), and his Bacon number is 3 (by
embarrassing himself on Jeopardy!).
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20221110/1beb286e/attachment.html>