Show simple item record

dc.contributor.authorPavlick, Ellie
dc.date.accessioned2021-04-06T15:39:09Z
dc.date.available2021-04-06T15:39:09Z
dc.date.issued2021-03-24
dc.identifier.urihttp://hdl.handle.net/1853/64417
dc.descriptionPresented online on March 24, 2021 at 12:15 p.m.en_US
dc.descriptionEllie Pavlick is an Assistant Professor of Computer Science at Brown University where she leads the Language Understanding and Representation (LUNAR) Lab. She received her PhD from the one-and-only University of Pennsylvania. Her current work focuses on building more cognitively-plausible models of natural language semantics, focusing on grounded language learning and on sample efficiency and generalization of neural language models.
dc.descriptionRuntime: 57:05 minutes
dc.description.abstractA wave of recent work has sought to understand how pretrained language models work. Such analyses have resulted in two seemingly contradictory sets of results. On one hand, work based on "probing classifiers" generally suggests that SOTA language models contain rich information about linguistic structure (e.g., parts of speech, syntax, semantic roles). On the other hand, work which measures performance on linguistic "challenge sets" shows that models consistently fail to use this information when making predictions. In this talk, I will present a series of results that attempt to bridge this gap. Our recent experiments suggest that the disconnect is not due to catastrophic forgetting nor is it (entirely) explained by insufficient training data. Rather, it is best explained in terms of how "accessible" features are to the model following pretraining, where "accessibility" can be quantified using an information-theoretic interpretation of probing classifiers.en_US
dc.format.extent57:05 minutes
dc.language.isoen_USen_US
dc.relation.ispartofseriesML@GT Seminar Series;
dc.subjectLanguage modelsen_US
dc.subjectNatural language processing (NLP)en_US
dc.titleYou can lead a horse to water...: Representing vs. Using Features in Neural NLPen_US
dc.typeLectureen_US
dc.typeVideoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Machine Learningen_US
dc.contributor.corporatenameBrown University. Dept. of Computer Scienceen_US
dc.contributor.corporatenameGoogle AIen_US


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record