Abstract
Sentiment analysis is an important task in natural language processing (NLP). Most of existing state-of-the-art methods are under the supervised learning paradigm. However, human annotations can be scarce. Thus, we should leverage more weak supervision for sentiment analysis. In this paper, we propose a posterior regularization framework for the variational approach to the weakly supervised sentiment analysis to better control the posterior distribution of the label assignment. The intuition behind the posterior regularization is that if extracted opinion words from two documents are semantically similar, the posterior distributions of two documents should be similar. Our experimental results show that the posterior regularization can improve the original variational approach to the weakly supervised sentiment analysis and the performance is more stable with smaller prediction variance.- Anthology ID:
- 2021.eacl-main.285
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3259–3268
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.285
- DOI:
- 10.18653/v1/2021.eacl-main.285
- Cite (ACL):
- Ziqian Zeng and Yangqiu Song. 2021. Variational Weakly Supervised Sentiment Analysis with Posterior Regularization. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3259–3268, Online. Association for Computational Linguistics.
- Cite (Informal):
- Variational Weakly Supervised Sentiment Analysis with Posterior Regularization (Zeng & Song, EACL 2021)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2021.eacl-main.285.pdf
- Code
- HKUST-KnowComp/VWS-PR
- Data
- IMDb Movie Reviews