Abstract
Targeted sentiment analysis is the task of jointly predicting target entities and their associated sentiment information. Existing research efforts mostly regard this joint task as a sequence labeling problem, building models that can capture explicit structures in the output space. However, the importance of capturing implicit global structural information that resides in the input space is largely unexplored. In this work, we argue that both types of information (implicit and explicit structural information) are crucial for building a successful targeted sentiment analysis model. Our experimental results show that properly capturing both information is able to lead to better performance than competitive existing approaches. We also conduct extensive experiments to investigate our model’s effectiveness and robustness.- Anthology ID:
- D19-1550
- 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:
- 5478–5488
- Language:
- URL:
- https://aclanthology.org/D19-1550
- DOI:
- 10.18653/v1/D19-1550
- Cite (ACL):
- Hao Li and Wei Lu. 2019. Learning Explicit and Implicit Structures for Targeted 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 5478–5488, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Learning Explicit and Implicit Structures for Targeted Sentiment Analysis (Li & Lu, EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/D19-1550.pdf