JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection

• DOI: 10.18653/v1/2022.acl-long.7
• Publication Date: 2022-06-03T01:34:53Z
• Authors: Bin Liang; Qinglin Zhu; Xiang Li; Min Yang; Lin Gui; Yulan He; Ruifeng Xu
• Keywords: Q1; 01 natural sciences; P1; QA76; 0105 earth and related environmental sciences

Zero-shot stance detection (ZSSD) aims to detect the stance for an unseen target during the inference stage. In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastive learning and target-aware prototypical graph contrastive learning. Specifically, a stance contrastive learning strategy is employed to better generalize stance features for unseen targets. Further, we build a prototypical graph for each instance to learn the target-based representation, in which the prototypes are deployed as a bridge to share the graph structures between the known targets and the unseen ones. Then a novel target-aware prototypical graph contrastive learning strategy is devised to generalize the reasoning ability of target-based stance representations to the unseen targets. Extensive experiments on three benchmark datasets show that the proposed approach achieves state-ofthe- art performance in the ZSSD task.