Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks

Shubham Toshniwal, Sam Wiseman, Allyson Ettinger, Karen Livescu, Kevin Gimpel


Abstract
Long document coreference resolution remains a challenging task due to the large memory and runtime requirements of current models. Recent work doing incremental coreference resolution using just the global representation of entities shows practical benefits but requires keeping all entities in memory, which can be impractical for long documents. We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time, thus guaranteeing a linear runtime in length of document. We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy
Anthology ID:
2020.emnlp-main.685
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8519–8526
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.685
DOI:
10.18653/v1/2020.emnlp-main.685
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.685.pdf