Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling
Liwen Wang, Xuefeng Li, Jiachi Liu, Keqing He, Yuanmeng Yan, Weiran Xu
Abstract
Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research. However, as most of the existing methods do not achieve effective knowledge transfer to the target domain, they just fit the distribution of the seen slot and show poor performance on unseen slot in the target domain. To solve this, we propose a novel approach based on prototypical contrastive learning with a dynamic label confusion strategy for zero-shot slot filling. The prototypical contrastive learning aims to reconstruct the semantic constraints of labels, and we introduce the label confusion strategy to establish the label dependence between the source domains and the target domain on-the-fly. Experimental results show that our model achieves significant improvement on the unseen slots, while also set new state-of-the-arts on slot filling task.- Anthology ID:
- 2021.emnlp-main.746
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9474–9480
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.746
- DOI:
- 10.18653/v1/2021.emnlp-main.746
- Cite (ACL):
- Liwen Wang, Xuefeng Li, Jiachi Liu, Keqing He, Yuanmeng Yan, and Weiran Xu. 2021. Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9474–9480, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling (Wang et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.emnlp-main.746.pdf
- Code
- w-lw/pclc