Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack

Keqing He, Jinchao Zhang, Yuanmeng Yan, Weiran Xu, Cheng Niu, Jie Zhou


Abstract
Zero-shot slot filling has widely arisen to cope with data scarcity in target domains. However, previous approaches often ignore constraints between slot value representation and related slot description representation in the latent space and lack enough model robustness. In this paper, we propose a Contrastive Zero-Shot Learning with Adversarial Attack (CZSL-Adv) method for the cross-domain slot filling. The contrastive loss aims to map slot value contextual representations to the corresponding slot description representations. And we introduce an adversarial attack training strategy to improve model robustness. Experimental results show that our model significantly outperforms state-of-the-art baselines under both zero-shot and few-shot settings.
Anthology ID:
2020.coling-main.126
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1461–1467
Language:
URL:
https://aclanthology.org/2020.coling-main.126
DOI:
10.18653/v1/2020.coling-main.126
Bibkey:
Cite (ACL):
Keqing He, Jinchao Zhang, Yuanmeng Yan, Weiran Xu, Cheng Niu, and Jie Zhou. 2020. Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1461–1467, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack (He et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2020.coling-main.126.pdf
Data
SNIPS