Efficient Hybrid Generation Framework for Aspect-Based Sentiment Analysis

Haoran Lv, Junyi Liu, Henan Wang, Yaoming Wang, Jixiang Luo, Yaxiao Liu


Abstract
Aspect-based sentiment analysis (ABSA) has attracted broad attention due to its commercial value. Natural Language Generation-based (NLG) approaches dominate the recent advance in ABSA tasks. However, current NLG practices are inefficient because most of them directly employ an autoregressive generation framework that cannot efficiently generate location information and semantic representations of ABSA targets. In this paper, we propose a novel framework, namely Efficient Hybrid Generation (EHG) to revolutionize traditions. Specifically, we leverage an Efficient Hybrid Transformer to generate the location and semantic information of ABSA targets in parallel. Besides, we design a novel global hybrid loss function in combination with bipartite matching to achieve end-to-end model training. Extensive experiments demonstrate that our proposed EHG framework outperforms current state-of-the-art methods in almost all cases and outperforms existing NLG-based methods in terms of inference efficiency.
Anthology ID:
2023.eacl-main.71
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1007–1018
Language:
URL:
https://aclanthology.org/2023.eacl-main.71
DOI:
10.18653/v1/2023.eacl-main.71
Bibkey:
Cite (ACL):
Haoran Lv, Junyi Liu, Henan Wang, Yaoming Wang, Jixiang Luo, and Yaxiao Liu. 2023. Efficient Hybrid Generation Framework for Aspect-Based Sentiment Analysis. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1007–1018, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Efficient Hybrid Generation Framework for Aspect-Based Sentiment Analysis (Lv et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.71.pdf
Video:
 https://aclanthology.org/2023.eacl-main.71.mp4