Abstract
The state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms. However, the extraction of aspect-sentiment pairs lacks opinion terms as a reference, while co-extraction of aspect and opinion terms would not lead to meaningful pairs without determining their sentiment dependencies. To address the issue, we present a novel view of ABSA as an opinion triplet extraction task, and propose a multi-task learning framework to jointly extract aspect terms and opinion terms, and simultaneously parses sentiment dependencies between them with a biaffine scorer. At inference phase, the extraction of triplets is facilitated by a triplet decoding method based on the above outputs. We evaluate the proposed framework on four SemEval benchmarks for ASBA. The results demonstrate that our approach significantly outperforms a range of strong baselines and state-of-the-art approaches.- Anthology ID:
- 2020.findings-emnlp.72
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 819–828
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.72
- DOI:
- 10.18653/v1/2020.findings-emnlp.72
- Cite (ACL):
- Chen Zhang, Qiuchi Li, Dawei Song, and Benyou Wang. 2020. A Multi-task Learning Framework for Opinion Triplet Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 819–828, Online. Association for Computational Linguistics.
- Cite (Informal):
- A Multi-task Learning Framework for Opinion Triplet Extraction (Zhang et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.findings-emnlp.72.pdf
- Code
- GeneZC/OTE-MTL + additional community code