Meta-Learning for Few-Shot NMT Adaptation

Amr Sharaf, Hany Hassan, Hal Daumé III


Abstract
We present META-MT, a meta-learning approach to adapt Neural Machine Translation (NMT) systems in a few-shot setting. META-MT provides a new approach to make NMT models easily adaptable to many target do- mains with the minimal amount of in-domain data. We frame the adaptation of NMT systems as a meta-learning problem, where we learn to adapt to new unseen domains based on simulated offline meta-training domain adaptation tasks. We evaluate the proposed meta-learning strategy on ten domains with general large scale NMT systems. We show that META-MT significantly outperforms classical domain adaptation when very few in- domain examples are available. Our experiments shows that META-MT can outperform classical fine-tuning by up to 2.5 BLEU points after seeing only 4, 000 translated words (300 parallel sentences).
Anthology ID:
2020.ngt-1.5
Volume:
Proceedings of the Fourth Workshop on Neural Generation and Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Alexandra Birch, Andrew Finch, Hiroaki Hayashi, Kenneth Heafield, Marcin Junczys-Dowmunt, Ioannis Konstas, Xian Li, Graham Neubig, Yusuke Oda
Venue:
NGT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
43–53
Language:
URL:
https://aclanthology.org/2020.ngt-1.5
DOI:
10.18653/v1/2020.ngt-1.5
Bibkey:
Cite (ACL):
Amr Sharaf, Hany Hassan, and Hal Daumé III. 2020. Meta-Learning for Few-Shot NMT Adaptation. In Proceedings of the Fourth Workshop on Neural Generation and Translation, pages 43–53, Online. Association for Computational Linguistics.
Cite (Informal):
Meta-Learning for Few-Shot NMT Adaptation (Sharaf et al., NGT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.ngt-1.5.pdf
Video:
 http://slideslive.com/38929818