Neural Models for Reasoning over Multiple Mentions Using Coreference

Bhuwan Dhingra, Qiao Jin, Zhilin Yang, William Cohen, Ruslan Salakhutdinov


Abstract
Many problems in NLP require aggregating information from multiple mentions of the same entity which may be far apart in the text. Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not suited to such tasks. We present a recurrent layer which is instead biased towards coreferent dependencies. The layer uses coreference annotations extracted from an external system to connect entity mentions belonging to the same cluster. Incorporating this layer into a state-of-the-art reading comprehension model improves performance on three datasets – Wikihop, LAMBADA and the bAbi AI tasks – with large gains when training data is scarce.
Anthology ID:
N18-2007
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
42–48
Language:
URL:
https://aclanthology.org/N18-2007
DOI:
10.18653/v1/N18-2007
Bibkey:
Cite (ACL):
Bhuwan Dhingra, Qiao Jin, Zhilin Yang, William Cohen, and Ruslan Salakhutdinov. 2018. Neural Models for Reasoning over Multiple Mentions Using Coreference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 42–48, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Neural Models for Reasoning over Multiple Mentions Using Coreference (Dhingra et al., NAACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/N18-2007.pdf
Data
LAMBADAWikiHop