Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation

42Citations
Citations of this article
78Readers
Mendeley users who have this article in their library.

Abstract

Meta-learning has been sufficiently validated to be beneficial for low-resource neural machine translation (NMT). However, we find that meta-trained NMT fails to improve the translation performance of the domain unseen at the metatraining stage. In this paper, we aim to alleviate this issue by proposing a novel meta-curriculum learning for domain adaptation in NMT. During meta-training, the NMT first learns the similar curricula from each domain to avoid falling into a bad local optimum early, and finally learns the curricula of individualities to improve the model robustness for learning domain-specific knowledge. Experimental results on 10 different low-resource domains show that meta-curriculum learning can improve the translation performance of both familiar and unfamiliar domains.

Cite

CITATION STYLE

APA

Zhan, R., Liu, X., Wong, D. F., & Chao, L. S. (2021). Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation. In 35th AAAI Conference on Artificial Intelligence, AAAI 2021 (Vol. 16, pp. 14310–14318). Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v35i16.17683

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free