Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification

Hao Tang, Donghong Ji, Chenliang Li, Qiji Zhou


Abstract
Aspect-based sentiment classification is a popular task aimed at identifying the corresponding emotion of a specific aspect. One sentence may contain various sentiments for different aspects. Many sophisticated methods such as attention mechanism and Convolutional Neural Networks (CNN) have been widely employed for handling this challenge. Recently, semantic dependency tree implemented by Graph Convolutional Networks (GCN) is introduced to describe the inner connection between aspects and the associated emotion words. But the improvement is limited due to the noise and instability of dependency trees. To this end, we propose a dependency graph enhanced dual-transformer network (named DGEDT) by jointly considering the flat representations learnt from Transformer and graph-based representations learnt from the corresponding dependency graph in an iterative interaction manner. Specifically, a dual-transformer structure is devised in DGEDT to support mutual reinforcement between the flat representation learning and graph-based representation learning. The idea is to allow the dependency graph to guide the representation learning of the transformer encoder and vice versa. The results on five datasets demonstrate that the proposed DGEDT outperforms all state-of-the-art alternatives with a large margin.
Anthology ID:
2020.acl-main.588
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6578–6588
Language:
URL:
https://aclanthology.org/2020.acl-main.588
DOI:
10.18653/v1/2020.acl-main.588
Bibkey:
Cite (ACL):
Hao Tang, Donghong Ji, Chenliang Li, and Qiji Zhou. 2020. Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6578–6588, Online. Association for Computational Linguistics.
Cite (Informal):
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (Tang et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.588.pdf
Dataset:
 2020.acl-main.588.Dataset.zip
Video:
 http://slideslive.com/38928780