Abstract
We directly embed easily extractable discourse structure information (subsection, paragraph and text type) in a transformer-based Dutch event coreference resolution model in order to more explicitly provide it with structural information that is known to be important in coreferential relationships. Results show that integrating this type of knowledge leads to a significant improvement in CONLL F1 for within-document settings (+ 8.6\%) and a minor improvement for cross-document settings (+ 1.1\%).- Anthology ID:
- 2023.codi-1.5
- Volume:
- Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- CODI
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 48–53
- Language:
- URL:
- https://aclanthology.org/2023.codi-1.5
- DOI:
- 10.18653/v1/2023.codi-1.5
- Cite (ACL):
- Loic De Langhe, Orphee De Clercq, and Veronique Hoste. 2023. Leveraging Structural Discourse Information for Event Coreference Resolution in Dutch. In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 48–53, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Leveraging Structural Discourse Information for Event Coreference Resolution in Dutch (De Langhe et al., CODI 2023)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2023.codi-1.5.pdf