TY - GEN
T1 - JointCL
T2 - 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
AU - Liang, Bin
AU - Zhu, Qinglin
AU - Li, Xiang
AU - Yang, Min
AU - Gui, Lin
AU - He, Yulan
AU - Xu, Ruifeng
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85140201330
U2 - 10.18653/v1/2022.acl-long.7
DO - 10.18653/v1/2022.acl-long.7
M3 - 会议稿件
AN - SCOPUS:85140201330
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 81
EP - 91
BT - ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
A2 - Muresan, Smaranda
A2 - Nakov, Preslav
A2 - Villavicencio, Aline
PB - Association for Computational Linguistics (ACL)
Y2 - 22 May 2022 through 27 May 2022
ER -