Exploring Task Difficulty for Few-Shot Relation Extraction

Jiale Han, Bo Cheng, Wei Lu


Abstract
Few-shot relation extraction (FSRE) focuses on recognizing novel relations by learning with merely a handful of annotated instances. Meta-learning has been widely adopted for such a task, which trains on randomly generated few-shot tasks to learn generic data representations. Despite impressive results achieved, existing models still perform suboptimally when handling hard FSRE tasks, where the relations are fine-grained and similar to each other. We argue this is largely because existing models do not distinguish hard tasks from easy ones in the learning process. In this paper, we introduce a novel approach based on contrastive learning that learns better representations by exploiting relation label information. We further design a method that allows the model to adaptively learn how to focus on hard tasks. Experiments on two standard datasets demonstrate the effectiveness of our method.
Anthology ID:
2021.emnlp-main.204
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:
2605–2616
Language:
URL:
https://aclanthology.org/2021.emnlp-main.204
DOI:
10.18653/v1/2021.emnlp-main.204
Bibkey:
Cite (ACL):
Jiale Han, Bo Cheng, and Wei Lu. 2021. Exploring Task Difficulty for Few-Shot Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2605–2616, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Exploring Task Difficulty for Few-Shot Relation Extraction (Han et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.204.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.204.mp4
Code
 hanjiale/hcrp
Data
FewRelFewRel 2.0