Word-Level Coreference Resolution

Vladimir Dobrovolskii


Abstract
Recent coreference resolution models rely heavily on span representations to find coreference links between word spans. As the number of spans is O(n2) in the length of text and the number of potential links is O(n4), various pruning techniques are necessary to make this approach computationally feasible. We propose instead to consider coreference links between individual words rather than word spans and then reconstruct the word spans. This reduces the complexity of the coreference model to O(n2) and allows it to consider all potential mentions without pruning any of them out. We also demonstrate that, with these changes, SpanBERT for coreference resolution will be significantly outperformed by RoBERTa. While being highly efficient, our model performs competitively with recent coreference resolution systems on the OntoNotes benchmark.
Anthology ID:
2021.emnlp-main.605
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7670–7675
Language:
URL:
https://aclanthology.org/2021.emnlp-main.605
DOI:
10.18653/v1/2021.emnlp-main.605
Bibkey:
Cite (ACL):
Vladimir Dobrovolskii. 2021. Word-Level Coreference Resolution. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7670–7675, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Word-Level Coreference Resolution (Dobrovolskii, EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.605.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.605.mp4
Code
 vdobrovolskii/wl-coref
Data
CoNLLCoNLL-2012OntoNotes 5.0