[CaCL] CaCL Paper for 9/10

[Lewis, Ashley L.]

Hi everyone,

Here’s the paper we’ll be discussing this week: https://www.aclweb.org/anthology/P19-1452/. The abstract is below.

Here’s the Zoom link for Thursday (9/10) https://osu.zoom.us/j/94712017994?pwd=cVdNUGRSMkMyU2R0dTZaZ2xnSmxjUT09

Abstract:
Pre-trained text encoders have rapidly advanced the state of the art on many NLP tasks. We focus on one such model, BERT, and aim to quantify where linguistic information is captured within the network. We find that the model represents the steps of the traditional NLP pipeline in an interpretable and localizable way, and that the regions responsible for each step appear in the expected sequence: POS tagging, parsing, NER, semantic roles, then coreference. Qualitative analysis reveals that the model can and often does adjust this pipeline dynamically, revising lower-level decisions on the basis of disambiguating information from higher-level representations.

See you then!
Ash
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osu.edu/pipermail/cacl/attachments/20200903/fd540a68/attachment.html>