An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis

Yunlong Liang, Fandong Meng, Jinchao Zhang, Yufeng Chen, Jinan Xu, Jie Zhou


Abstract
Aspect-based sentiment analysis (ABSA) mainly involves three subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification, which are typically handled in a separate or joint manner. However, previous approaches do not well exploit the interactive relations among three subtasks and do not pertinently leverage the easily available document-level labeled domain/sentiment knowledge, which restricts their performances. To address these issues, we propose a novel Iterative Multi-Knowledge Transfer Network (IMKTN) for end-to-end ABSA. For one thing, through the interactive correlations between the ABSA subtasks, our IMKTN transfers the task-specific knowledge from any two of the three subtasks to another one at the token level by utilizing a well-designed routing algorithm, that is, any two of the three subtasks will help the third one. For another, our IMKTN pertinently transfers the document-level knowledge, i.e., domain-specific and sentiment-related knowledge, to the aspect-level subtasks to further enhance the corresponding performance. Experimental results on three benchmark datasets demonstrate the effectiveness and superiority of our approach.
Anthology ID:
2021.findings-emnlp.152
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1768–1780
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.152
DOI:
10.18653/v1/2021.findings-emnlp.152
Bibkey:
Cite (ACL):
Yunlong Liang, Fandong Meng, Jinchao Zhang, Yufeng Chen, Jinan Xu, and Jie Zhou. 2021. An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1768–1780, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis (Liang et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2021.findings-emnlp.152.pdf
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2021.findings-emnlp.152.mp4
Code
 XL2248/IKTN +  additional community code