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
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.findings-emnlp.152.pdf
- Code
- XL2248/IKTN + additional community code