Task-Specific Data Augmentation for Zero-shot and Few-shot Stance Detection

Jiarui Zhang, Shaojuan Wu, Xiaowang Zhang, Zhiyong Feng

Abstract

Various targets keep coming up on social media, and most of them lack labeled data. In this paper, we focus on zero-shot and few-shot stance detection, which aims to identify stances with few or even no training instances. In order to solve the lack of labeled data and implicit stance expression, we propose a self-supervised data augment approach based on coreference resolution. The method is specific for stance detection to generate more stable data and reduce the variance within and between classes to achieve a balance between validity and robustness. Considering the diversity of comments, we propose a novel multi-task stance detection framework of target-related fragment extraction and stance detection, which can enhance attention on target-related fragments and reduce the noise of other fragments. Experiments show that the proposed approach achieves state-of-the-art performance in zero-shot and few-shot stance detection.
BibTeX
@inproceedings{zhang2023task,
  author = {Jiarui Zhang and Shaojuan Wu and Xiaowang Zhang and Zhiyong Feng},
  title = {{Task-Specific Data Augmentation for Zero-shot and Few-shot Stance Detection}},
  booktitle = {The Web Conference},
  year = {2023},
  doi = {10.1145/3543873.3587337},
}

Loading related content...

Figure