Abstract
Stance detection is important for understanding different attitudes and beliefs on the Internet. However, given that a passage’s stance toward a given topic is often highly dependent on that topic, building a stance detection model that generalizes to unseen topics is difficult. In this work, we propose using contrastive learning as well as an unlabeled dataset of news articles that cover a variety of different topics to train topic-agnostic/TAG and topic-aware/TAW embeddings for use in downstream stance detection. Combining these embeddings in our full TATA model, we achieve state-of-the-art performance across several public stance detection datasets (0.771 F1-score on the Zero-shot VAST dataset). We release our code and data at https://github.com/hanshanley/tata.- Anthology ID:
- 2023.emnlp-main.694
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11280–11294
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.694
- DOI:
- 10.18653/v1/2023.emnlp-main.694
- Cite (ACL):
- Hans Hanley and Zakir Durumeric. 2023. TATA: Stance Detection via Topic-Agnostic and Topic-Aware Embeddings. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11280–11294, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- TATA: Stance Detection via Topic-Agnostic and Topic-Aware Embeddings (Hanley & Durumeric, EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.emnlp-main.694.pdf