The Referential Reader: A Recurrent Entity Network for Anaphora Resolution

Fei Liu, Luke Zettlemoyer, Jacob Eisenstein


Abstract
We present a new architecture for storing and accessing entity mentions during online text processing. While reading the text, entity references are identified, and may be stored by either updating or overwriting a cell in a fixed-length memory. The update operation implies coreference with the other mentions that are stored in the same cell; the overwrite operation causes these mentions to be forgotten. By encoding the memory operations as differentiable gates, it is possible to train the model end-to-end, using both a supervised anaphora resolution objective as well as a supplementary language modeling objective. Evaluation on a dataset of pronoun-name anaphora demonstrates strong performance with purely incremental text processing.
Anthology ID:
P19-1593
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5918–5925
Language:
URL:
https://aclanthology.org/P19-1593
DOI:
10.18653/v1/P19-1593
Bibkey:
Cite (ACL):
Fei Liu, Luke Zettlemoyer, and Jacob Eisenstein. 2019. The Referential Reader: A Recurrent Entity Network for Anaphora Resolution. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5918–5925, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
The Referential Reader: A Recurrent Entity Network for Anaphora Resolution (Liu et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/P19-1593.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/P19-1593.mp4
Code
 liufly/refreader
Data
GAP Coreference Dataset