ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475876" target="_blank" >RIV/00216208:11320/23:10475876 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution
Original language description
We present CorPipe, the winning entry to the CRAC 2023 Shared Task on Multilingual Coreference Resolution. Our system is an improved version of our earlier multilingual coreference pipeline, and it surpasses other participants by a large margin of 4.5 percent points. CorPipe first performs mention detection, followed by coreference linking via an antecedent-maximization approach on the retrieved spans. Both tasks are trained jointly on all available corpora using a shared pretrained language model. Our main improvements comprise inputs larger than 512 subwords and changing the mention decoding to support ensembling. The source code is available at https://github.com/ufal/crac2023-corpipe.
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
<a href="/en/project/GX20-16819X" target="_blank" >GX20-16819X: Language Understanding: from Syntax to Discourse</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the CRAC 2023 Shared Task on Multilingual Coreference Resolution
ISBN
978-1-955917-02-5
ISSN
—
e-ISSN
—
Number of pages
11
Pages from-to
41-51
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Singapore
Event date
Dec 6, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—