IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis

Navonil Majumder, Soujanya Poria, Alexander Gelbukh, Md. Shad Akhtar, Erik Cambria, Asif Ekbal


Abstract
Sentiment analysis has immense implications in e-commerce through user feedback mining. Aspect-based sentiment analysis takes this one step further by enabling businesses to extract aspect specific sentimental information. In this paper, we present a novel approach of incorporating the neighboring aspects related information into the sentiment classification of the target aspect using memory networks. We show that our method outperforms the state of the art by 1.6% on average in two distinct domains: restaurant and laptop.
Anthology ID:
D18-1377
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3402–3411
Language:
URL:
https://aclanthology.org/D18-1377
DOI:
10.18653/v1/D18-1377
Bibkey:
Cite (ACL):
Navonil Majumder, Soujanya Poria, Alexander Gelbukh, Md. Shad Akhtar, Erik Cambria, and Asif Ekbal. 2018. IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3402–3411, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis (Majumder et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1377.pdf
Code
 senticnet/IARM
Data
SemEval 2014 Task 4 Sub Task 2