Abstract
Aspect-based sentiment analysis (ABSA) has attracted increasing attention recently due to its broad applications. In existing ABSA datasets, most sentences contain only one aspect or multiple aspects with the same sentiment polarity, which makes ABSA task degenerate to sentence-level sentiment analysis. In this paper, we present a new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset, in which each sentence contains at least two different aspects with different sentiment polarities. The release of this dataset would push forward the research in this field. In addition, we propose simple yet effective CapsNet and CapsNet-BERT models which combine the strengths of recent NLP advances. Experiments on our new dataset show that the proposed model significantly outperforms the state-of-the-art baseline methods- Anthology ID:
- D19-1654
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6280–6285
- Language:
- URL:
- https://aclanthology.org/D19-1654
- DOI:
- 10.18653/v1/D19-1654
- Cite (ACL):
- Qingnan Jiang, Lei Chen, Ruifeng Xu, Xiang Ao, and Min Yang. 2019. A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6280–6285, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis (Jiang et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D19-1654.pdf
- Code
- siat-nlp/MAMS-for-ABSA
- Data
- MAMS