Abstract
Current state-of-the-art coreference systems are based on a single pairwise scoring component, which assigns to each pair of mention spans a score reflecting their tendency to corefer to each other. We observe that different kinds of mention pairs require different information sources to assess their score. We present LingMess, a linguistically motivated categorization of mention-pairs into 6 types of coreference decisions and learn a dedicated trainable scoring function for each category. This significantly improves the accuracy of the pairwise scorer as well as of the overall coreference performance on the English Ontonotes coreference corpus and 5 additional datasets.- Anthology ID:
- 2023.eacl-main.202
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2752–2760
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.202
- DOI:
- 10.18653/v1/2023.eacl-main.202
- Cite (ACL):
- Shon Otmazgin, Arie Cattan, and Yoav Goldberg. 2023. LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2752–2760, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution (Otmazgin et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2023.eacl-main.202.pdf