Research Area:  Machine Learning

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 meta-training 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.

Keywords:  
Machine Translation
Multilinguality
Meta-learning
Neural machine translation
meta-training stage

Author(s) Name:   Runzhe Zhan, Xuebo Liu, Derek F. Wong

Publisher name:  AAAI

DOI:  10.1609/aaai.v35i16.17683

Volume Information:  

Paper Link:   https://ojs.aaai.org/index.php/AAAI/article/view/17683