McGill at CRAC 2023: Multilingual Generalization of Entity-Ranking Coreference Resolution Models

Ian Porada, Jackie Chi Kit Cheung


Abstract
Our submission to the CRAC 2023 shared task, described herein, is an adapted entity-ranking model jointly trained on all 17 datasets spanning 12 languages. Our model outperforms the shared task baselines by a difference in F1 score of +8.47, achieving an ultimate F1 score of 65.43 and fourth place in the shared task. We explore design decisions related to data preprocessing, the pretrained encoder, and data mixing.
Anthology ID:
2023.crac-sharedtask.5
Volume:
Proceedings of the CRAC 2023 Shared Task on Multilingual Coreference Resolution
Month:
December
Year:
2023
Address:
Singapore
Editors:
Zdeněk Žabokrtský, Maciej Ogrodniczuk
Venues:
CRAC | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
52–57
Language:
URL:
https://aclanthology.org/2023.crac-sharedtask.5
DOI:
10.18653/v1/2023.crac-sharedtask.5
Bibkey:
Cite (ACL):
Ian Porada and Jackie Chi Kit Cheung. 2023. McGill at CRAC 2023: Multilingual Generalization of Entity-Ranking Coreference Resolution Models. In Proceedings of the CRAC 2023 Shared Task on Multilingual Coreference Resolution, pages 52–57, Singapore. Association for Computational Linguistics.
Cite (Informal):
McGill at CRAC 2023: Multilingual Generalization of Entity-Ranking Coreference Resolution Models (Porada & Cheung, CRAC-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.crac-sharedtask.5.pdf