Coreference for Discourse Parsing: A Neural Approach

Grigorii Guz, Giuseppe Carenini


Abstract
We present preliminary results on investigating the benefits of coreference resolution features for neural RST discourse parsing by considering different levels of coupling of the discourse parser with the coreference resolver. In particular, starting with a strong baseline neural parser unaware of any coreference information, we compare a parser which utilizes only the output of a neural coreference resolver, with a more sophisticated model, where discourse parsing and coreference resolution are jointly learned in a neural multitask fashion. Results indicate that these initial attempts to incorporate coreference information do not boost the performance of discourse parsing in a statistically significant way.
Anthology ID:
2020.codi-1.17
Volume:
Proceedings of the First Workshop on Computational Approaches to Discourse
Month:
November
Year:
2020
Address:
Online
Editors:
Chloé Braud, Christian Hardmeier, Junyi Jessy Li, Annie Louis, Michael Strube
Venue:
CODI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
160–167
Language:
URL:
https://aclanthology.org/2020.codi-1.17
DOI:
10.18653/v1/2020.codi-1.17
Bibkey:
Cite (ACL):
Grigorii Guz and Giuseppe Carenini. 2020. Coreference for Discourse Parsing: A Neural Approach. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 160–167, Online. Association for Computational Linguistics.
Cite (Informal):
Coreference for Discourse Parsing: A Neural Approach (Guz & Carenini, CODI 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.codi-1.17.pdf
Video:
 https://slideslive.com/38939706