Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning

Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Dejing Dou, Thien Huu Nguyen


Abstract
Targeted opinion word extraction (TOWE) is a sub-task of aspect based sentiment analysis (ABSA) which aims to find the opinion words for a given aspect-term in a sentence. Despite their success for TOWE, the current deep learning models fail to exploit the syntactic information of the sentences that have been proved to be useful for TOWE in the prior research. In this work, we propose to incorporate the syntactic structures of the sentences into the deep learning models for TOWE, leveraging the syntax-based opinion possibility scores and the syntactic connections between the words. We also introduce a novel regularization technique to improve the performance of the deep learning models based on the representation distinctions between the words in TOWE. The proposed model is extensively analyzed and achieves the state-of-the-art performance on four benchmark datasets.
Anthology ID:
2020.emnlp-main.719
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:
8947–8956
Language:
URL:
https://aclanthology.org/2020.emnlp-main.719
DOI:
10.18653/v1/2020.emnlp-main.719
Bibkey:
Cite (ACL):
Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Dejing Dou, and Thien Huu Nguyen. 2020. Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8947–8956, Online. Association for Computational Linguistics.
Cite (Informal):
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning (Pouran Ben Veyseh et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.719.pdf
Video:
 https://slideslive.com/38939322
Data
SemEval 2014 Task 4 Sub Task 2