Abstract
Machine learning approaches to coreference resolution vary greatly in the modeling of the problem: while early approaches operated on the mention pair level, current research focuses on ranking architectures and antecedent trees. We propose a unified representation of different approaches to coreference resolution in terms of the structure they operate on. We represent several coreference resolution approaches proposed in the literature in our framework and evaluate their performance. Finally, we conduct a systematic analysis of the output of these approaches, highlighting differences and similarities.- Anthology ID:
- Q15-1029
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 3
- Month:
- Year:
- 2015
- Address:
- Cambridge, MA
- Editors:
- Michael Collins, Lillian Lee
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 405–418
- Language:
- URL:
- https://aclanthology.org/Q15-1029
- DOI:
- 10.1162/tacl_a_00147
- Cite (ACL):
- Sebastian Martschat and Michael Strube. 2015. Latent Structures for Coreference Resolution. Transactions of the Association for Computational Linguistics, 3:405–418.
- Cite (Informal):
- Latent Structures for Coreference Resolution (Martschat & Strube, TACL 2015)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/Q15-1029.pdf