ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification
Wangjie Jiang, Zhihao Ye, Bang Liu, Ruihui Zhao, Jianguang Zheng, Mengyao Li, Zhiyong Li, Yujiu Yang, Yefeng Zheng
Abstract
In the task of incremental few-shot relation classification, model performance is always limited by the incompatibility between the base feature embedding space and the novel feature embedding space. To tackle the issue, we propose a novel model named ICA-Proto: Iterative Cross Alignment prototypical network. Specifically, we incorporate the query representation into the encoding of novel prototypes and utilize the query-aware prototypes to update the query representation at the same time. Further, we implement the above process iteratively to achieve more interaction. In addition, a novel prototype quadruplet loss is designed to regulate the spatial distributions of embedding space, so as to make it easier for the relation classification. Experimental results on two benchmark datasets demonstrate that ICA-Proto significantly outperforms the state-of-the-art baseline model.- Anthology ID:
- 2023.findings-eacl.171
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2275–2284
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.171
- DOI:
- 10.18653/v1/2023.findings-eacl.171
- Cite (ACL):
- Wangjie Jiang, Zhihao Ye, Bang Liu, Ruihui Zhao, Jianguang Zheng, Mengyao Li, Zhiyong Li, Yujiu Yang, and Yefeng Zheng. 2023. ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2275–2284, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification (Jiang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.findings-eacl.171.pdf