When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AN52DUJYJ" target="_blank" >RIV/00216208:11320/25:N52DUJYJ - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204453336&partnerID=40&md5=ec3c66b3cdae014490482370d542278e" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204453336&partnerID=40&md5=ec3c66b3cdae014490482370d542278e</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality
Original language description
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. © 2024 Association for Computational Linguistics.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proc. Annu. Meet. Assoc. Comput Linguist.
ISBN
979-889176094-3
ISSN
0736-587X
e-ISSN
—
Number of pages
28
Pages from-to
4722-4749
Publisher name
Association for Computational Linguistics (ACL)
Place of publication
—
Event location
Bangkok
Event date
Jan 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—