CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492906" target="_blank" >RIV/00216208:11320/24:10492906 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2024.crac-1.9/" target="_blank" >https://aclanthology.org/2024.crac-1.9/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text
Original language description
We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the shared task, a novel objective is to also predict empty nodes needed for zero coreference mentions (while the empty nodes were given on input in previous years). This way, coreference resolution can be performed on raw text. We evaluate two model variants: a two-stage approach (where the empty nodes are predicted first using a pretrained encoder model and then processed together with sentence words by another pretrained model) and a single-stage approach (where a single pretrained encoder model generates empty nodes, coreference mentions, and coreference links jointly). In both settings, CorPipe surpasses other participants by a large margin of 3.9 and 2.8 percent points, respectively. The source code and the trained model are available at https://github.com/ufal/crac2024-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
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
Proceedings of The Seventh Workshop on Computational Models of Reference, Anaphora and Coreference
ISBN
979-8-89176-171-1
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
97-106
Publisher name
Association for Computational Linguistics
Place of publication
Kerrville, TX, USA
Event location
Miami, FL, USA
Event date
Nov 15, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—