Meta-Information Guided Meta-Learning for Few-Shot Relation Classification

Bowen Dong, Yuan Yao, Ruobing Xie, Tianyu Gao, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun


Abstract
Few-shot classification requires classifiers to adapt to new classes with only a few training instances. State-of-the-art meta-learning approaches such as MAML learn how to initialize and fast adapt parameters from limited instances, which have shown promising results in few-shot classification. However, existing meta-learning models solely rely on implicit instance-based statistics, and thus suffer from instance unreliability and weak interpretability. To solve this problem, we propose a novel meta-information guided meta-learning (MIML) framework, where semantic concepts of classes provide strong guidance for meta-learning in both initialization and adaptation. In effect, our model can establish connections between instance-based information and semantic-based information, which enables more effective initialization and faster adaptation. Comprehensive experimental results on few-shot relation classification demonstrate the effectiveness of the proposed framework. Notably, MIML achieves comparable or superior performance to humans with only one shot on FewRel evaluation.
Anthology ID:
2020.coling-main.140
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1594–1605
Language:
URL:
https://aclanthology.org/2020.coling-main.140
DOI:
10.18653/v1/2020.coling-main.140
Bibkey:
Cite (ACL):
Bowen Dong, Yuan Yao, Ruobing Xie, Tianyu Gao, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, and Maosong Sun. 2020. Meta-Information Guided Meta-Learning for Few-Shot Relation Classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1594–1605, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Meta-Information Guided Meta-Learning for Few-Shot Relation Classification (Dong et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.140.pdf
Code
 thunlp/miml
Data
FewRel