Abstract
The goal of stance detection is to identify whether the author of a text is in favor of, neutral or against a specific target. Despite substantial progress on this task, one of the remaining challenges is the scarcity of annotations. Data augmentation is commonly used to address annotation scarcity by generating more training samples. However, the augmented sentences that are generated by existing methods are either less diversified or inconsistent with the given target and stance label. In this paper, we formulate the data augmentation of stance detection as a conditional masked language modeling task and augment the dataset by predicting the masked word conditioned on both its context and the auxiliary sentence that contains target and label information. Moreover, we propose another simple yet effective method that generates target-aware sentence by replacing a target mention with the other. Experimental results show that our proposed methods significantly outperforms previous augmentation methods on 11 targets.- Anthology ID:
- 2021.naacl-main.148
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1850–1860
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.148
- DOI:
- 10.18653/v1/2021.naacl-main.148
- Cite (ACL):
- Yingjie Li and Cornelia Caragea. 2021. Target-Aware Data Augmentation for Stance Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1850–1860, Online. Association for Computational Linguistics.
- Cite (Informal):
- Target-Aware Data Augmentation for Stance Detection (Li & Caragea, NAACL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.148.pdf