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

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-of-the-art performance in the ZSSD task(1).

Automated summary

This paper proposes a joint contrastive learning framework for zero-shot stance detection, which achieves state-of-the-art performance by generalizing stance features and reasoning ability for unseen targets through stance contrastive learning and target-aware prototypical graph contrastive learning.