Abstract
Aspect-level sentiment classification (ASC) aims to detect the sentiment polarity of a given opinion target in a sentence. In neural network-based methods for ASC, most works employ the attention mechanism to capture the corresponding sentiment words of the opinion target, then aggregate them as evidence to infer the sentiment of the target. However, aspect-level datasets are all relatively small-scale due to the complexity of annotation. Data scarcity causes the attention mechanism sometimes to fail to focus on the corresponding sentiment words of the target, which finally weakens the performance of neural models. To address the issue, we propose a novel Attention Transfer Network (ATN) in this paper, which can successfully exploit attention knowledge from resource-rich document-level sentiment classification datasets to improve the attention capability of the aspect-level sentiment classification task. In the ATN model, we design two different methods to transfer attention knowledge and conduct experiments on two ASC benchmark datasets. Extensive experimental results show that our methods consistently outperform state-of-the-art works. Further analysis also validates the effectiveness of ATN.- Anthology ID:
- 2020.coling-main.70
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 811–821
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.70
- DOI:
- 10.18653/v1/2020.coling-main.70
- Cite (ACL):
- Fei Zhao, Zhen Wu, and Xinyu Dai. 2020. Attention Transfer Network for Aspect-level Sentiment Classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 811–821, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Attention Transfer Network for Aspect-level Sentiment Classification (Zhao et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.70.pdf
- Code
- 1429904852/ATN
- Data
- SemEval-2014 Task-4