Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision

Abiola Obamuyide, Andreas Vlachos


Abstract
In this paper we frame the task of supervised relation classification as an instance of meta-learning. We propose a model-agnostic meta-learning protocol for training relation classifiers to achieve enhanced predictive performance in limited supervision settings. During training, we aim to not only learn good parameters for classifying relations with sufficient supervision, but also learn model parameters that can be fine-tuned to enhance predictive performance for relations with limited supervision. In experiments conducted on two relation classification datasets, we demonstrate that the proposed meta-learning approach improves the predictive performance of two state-of-the-art supervised relation classification models.
Anthology ID:
P19-1589
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5873–5879
Language:
URL:
https://aclanthology.org/P19-1589
DOI:
10.18653/v1/P19-1589
Bibkey:
Cite (ACL):
Abiola Obamuyide and Andreas Vlachos. 2019. Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5873–5879, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision (Obamuyide & Vlachos, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1589.pdf
Video:
 https://aclanthology.org/P19-1589.mp4