Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text

Li Zhenzhen, Yuyang Zhang, Jian-Yun Nie, Dongsheng Li


Abstract
Few-shot relation classification is difficult because the few instances available may not represent well the relation patterns. Some existing approaches explored extra information such as relation definition, in addition to the instances, to learn a better relation representation. However, the encoding of the extra information has been performed independently from the labeled instances. In this paper, we propose to learn a prototype encoder from relation definition in a way that is useful for relation instance classification. To this end, we use a joint training approach to train both a prototype encoder from definition and an instance encoder. Extensive experiments on several datasets demonstrate the effectiveness and usefulness of our prototype encoder from definition text, enabling us to outperform state-of-the-art approaches.
Anthology ID:
2022.findings-naacl.34
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
454–464
Language:
URL:
https://aclanthology.org/2022.findings-naacl.34
DOI:
10.18653/v1/2022.findings-naacl.34
Bibkey:
Cite (ACL):
Li Zhenzhen, Yuyang Zhang, Jian-Yun Nie, and Dongsheng Li. 2022. Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 454–464, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition Text (Zhenzhen et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.34.pdf
Video:
 https://aclanthology.org/2022.findings-naacl.34.mp4
Data
FewRelFewRel 2.0