Abstract
Most of the existing pre-trained language representation models neglect to consider the linguistic knowledge of texts, which can promote language understanding in NLP tasks. To benefit the downstream tasks in sentiment analysis, we propose a novel language representation model called SentiLARE, which introduces word-level linguistic knowledge including part-of-speech tag and sentiment polarity (inferred from SentiWordNet) into pre-trained models. We first propose a context-aware sentiment attention mechanism to acquire the sentiment polarity of each word with its part-of-speech tag by querying SentiWordNet. Then, we devise a new pre-training task called label-aware masked language model to construct knowledge-aware language representation. Experiments show that SentiLARE obtains new state-of-the-art performance on a variety of sentiment analysis tasks.- Anthology ID:
- 2020.emnlp-main.567
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6975–6988
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.567
- DOI:
- 10.18653/v1/2020.emnlp-main.567
- Cite (ACL):
- Pei Ke, Haozhe Ji, Siyang Liu, Xiaoyan Zhu, and Minlie Huang. 2020. SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6975–6988, Online. Association for Computational Linguistics.
- Cite (Informal):
- SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge (Ke et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.emnlp-main.567.pdf
- Code
- thu-coai/SentiLARE
- Data
- GLUE, IMDb Movie Reviews, SICK, SST