Abstract
Politicians often have underlying agendas when reacting to events. Arguments in contexts of various events reflect a fairly consistent set of agendas for a given entity. In spite of recent advances in Pretrained Language Models, those text representations are not designed to capture such nuanced patterns. In this paper, we propose a Compositional Reader model consisting of encoder and composer modules, that captures and leverages such information to generate more effective representations for entities, issues, and events. These representations are contextualized by tweets, press releases, issues, news articles, and participating entities. Our model processes several documents at once and generates composed representations for multiple entities over several issues or events. Via qualitative and quantitative empirical analysis, we show that these representations are meaningful and effective.- Anthology ID:
- 2021.emnlp-main.102
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1353–1367
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.102
- DOI:
- 10.18653/v1/2021.emnlp-main.102
- Cite (ACL):
- Rajkumar Pujari and Dan Goldwasser. 2021. Understanding Politics via Contextualized Discourse Processing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1353–1367, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Understanding Politics via Contextualized Discourse Processing (Pujari & Goldwasser, EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.102.pdf
- Code
- pujari-rajkumar/compositional_learner