Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis

Fei Liu, Trevor Cohn, Timothy Baldwin


Abstract
While neural networks have been shown to achieve impressive results for sentence-level sentiment analysis, targeted aspect-based sentiment analysis (TABSA) — extraction of fine-grained opinion polarity w.r.t. a pre-defined set of aspects — remains a difficult task. Motivated by recent advances in memory-augmented models for machine reading, we propose a novel architecture, utilising external “memory chains” with a delayed memory update mechanism to track entities. On a TABSA task, the proposed model demonstrates substantial improvements over state-of-the-art approaches, including those using external knowledge bases.
Anthology ID:
N18-2045
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:
278–283
Language:
URL:
https://aclanthology.org/N18-2045
DOI:
10.18653/v1/N18-2045
Bibkey:
Cite (ACL):
Fei Liu, Trevor Cohn, and Timothy Baldwin. 2018. Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis. 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 278–283, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis (Liu et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2045.pdf
Code
 liufly/delayed-memory-update-entnet
Data
CBT