Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction

Lu Xu, Yew Ken Chia, Lidong Bing


Abstract
Aspect Sentiment Triplet Extraction (ASTE) is the most recent subtask of ABSA which outputs triplets of an aspect target, its associated sentiment, and the corresponding opinion term. Recent models perform the triplet extraction in an end-to-end manner but heavily rely on the interactions between each target word and opinion word. Thereby, they cannot perform well on targets and opinions which contain multiple words. Our proposed span-level approach explicitly considers the interaction between the whole spans of targets and opinions when predicting their sentiment relation. Thus, it can make predictions with the semantics of whole spans, ensuring better sentiment consistency. To ease the high computational cost caused by span enumeration, we propose a dual-channel span pruning strategy by incorporating supervision from the Aspect Term Extraction (ATE) and Opinion Term Extraction (OTE) tasks. This strategy not only improves computational efficiency but also distinguishes the opinion and target spans more properly. Our framework simultaneously achieves strong performance for the ASTE as well as ATE and OTE tasks. In particular, our analysis shows that our span-level approach achieves more significant improvements over the baselines on triplets with multi-word targets or opinions.
Anthology ID:
2021.acl-long.367
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4755–4766
Language:
URL:
https://aclanthology.org/2021.acl-long.367
DOI:
10.18653/v1/2021.acl-long.367
Bibkey:
Cite (ACL):
Lu Xu, Yew Ken Chia, and Lidong Bing. 2021. Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4755–4766, Online. Association for Computational Linguistics.
Cite (Informal):
Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction (Xu et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.367.pdf
Video:
 https://aclanthology.org/2021.acl-long.367.mp4
Code
 chiayewken/Span-ASTE +  additional community code
Data
ASTEASTE-Data-V2MuseASTE