CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution

Milan Straka


Abstract
We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced development and test sets to lower computational requirements, and includes additional datasets. CorPipe 25 represents a complete reimplementation of our previous systems, migrating from TensorFlow to PyTorch. Our system significantly outperforms all other submissions in both the LLM and unconstrained tracks by a substantial margin of 8 percentage points. The source code and trained models are publicly available at https://github.com/ufal/crac2025-corpipe.
Anthology ID:
2025.crac-1.11
Volume:
Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Maciej Ogrodniczuk, Michal Novak, Massimo Poesio, Sameer Pradhan, Vincent Ng
Venue:
CRAC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
130–139
Language:
URL:
https://aclanthology.org/2025.crac-1.11/
DOI:
Bibkey:
Cite (ACL):
Milan Straka. 2025. CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution. In Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 130–139, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution (Straka, CRAC 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.crac-1.11.pdf