Towards Realistic Few-Shot Relation Extraction

Sam Brody, Sichao Wu, Adrian Benton


Abstract
In recent years, few-shot models have been applied successfully to a variety of NLP tasks. Han et al. (2018) introduced a few-shot learning framework for relation classification, and since then, several models have surpassed human performance on this task, leading to the impression that few-shot relation classification is solved. In this paper we take a deeper look at the efficacy of strong few-shot classification models in the more common relation extraction setting, and show that typical few-shot evaluation metrics obscure a wide variability in performance across relations. In particular, we find that state of the art few-shot relation classification models overly rely on entity type information, and propose modifications to the training routine to encourage models to better discriminate between relations involving similar entity types.
Anthology ID:
2021.emnlp-main.433
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5338–5345
Language:
URL:
https://aclanthology.org/2021.emnlp-main.433
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.433.pdf
Code
 bloomberg/emnlp21_fewrel
Data
FewRelFewRel 2.0