Lecture image placeholder

Premium content

Access to this content requires a subscription. You must be a premium user to view this content.

Monthly subscription - $9.99Pay per view - $4.99Access through your institutionLogin with Underline account
Need help?
Contact us
Lecture placeholder background
VIDEO DOI: https://doi.org/10.48448/abse-ne88

poster

ACL 2024

August 13, 2024

Bangkok, Thailand

When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality

keywords:

restart-incrementality

incremental processing

language model

interpretability

dependency parsing

Incremental models that process sentences one token at a time will sometimes encounter points where more than one interpretation is possible. Causal models are forced to output one interpretation and continue, whereas models that can revise may edit their previous output as the ambiguity is resolved. In this work, we look at how restart-incremental Transformers build and update internal states, in an effort to shed light on what processes cause revisions not viable in autoregressive models. We propose an interpretable way to analyse the incremental states, showing that their sequential structure encodes information on the garden path effect and its resolution. Our method brings insights on various bidirectional encoders for contextualised meaning representation and dependency parsing, contributing to show their advantage over causal models when it comes to revisions.

Downloads

SlidesTranscript English (automatic)

Next from ACL 2024

Planning Like Human: A Dual-process Framework for Dialogue Planning
poster

Planning Like Human: A Dual-process Framework for Dialogue Planning

ACL 2024

+4Yixin Cao
Tao He and 6 other authors

13 August 2024

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved