AMR-based Network for Aspect-based Sentiment Analysis

Fukun Ma, Xuming Hu, Aiwei Liu, Yawen Yang, Shuang Li, Philip S. Yu, Lijie Wen


Abstract
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment classification task. Many recent works have used dependency trees to extract the relation between aspects and contexts and have achieved significant improvements. However, further improvement is limited due to the potential mismatch between the dependency tree as a syntactic structure and the sentiment classification as a semantic task. To alleviate this gap, we replace the syntactic dependency tree with the semantic structure named Abstract Meaning Representation (AMR) and propose a model called AMR-based Path Aggregation Relational Network (APARN) to take full advantage of semantic structures. In particular, we design the path aggregator and the relation-enhanced self-attention mechanism that complement each other. The path aggregator extracts semantic features from AMRs under the guidance of sentence information, while the relation-enhanced self-attention mechanism in turn improves sentence features with refined semantic information. Experimental results on four public datasets demonstrate 1.13% average F1 improvement of APARN in ABSA when compared with state-of-the-art baselines.
Anthology ID:
2023.acl-long.19
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
322–337
Language:
URL:
https://aclanthology.org/2023.acl-long.19
DOI:
10.18653/v1/2023.acl-long.19
Bibkey:
Cite (ACL):
Fukun Ma, Xuming Hu, Aiwei Liu, Yawen Yang, Shuang Li, Philip S. Yu, and Lijie Wen. 2023. AMR-based Network for Aspect-based Sentiment Analysis. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 322–337, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
AMR-based Network for Aspect-based Sentiment Analysis (Ma et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.19.pdf
Video:
 https://aclanthology.org/2023.acl-long.19.mp4