%0 Conference Proceedings %T Meta-Learning for Few-Shot NMT Adaptation %A Sharaf, Amr %A Hassan, Hany %A Daumé III, Hal %Y Birch, Alexandra %Y Finch, Andrew %Y Hayashi, Hiroaki %Y Heafield, Kenneth %Y Junczys-Dowmunt, Marcin %Y Konstas, Ioannis %Y Li, Xian %Y Neubig, Graham %Y Oda, Yusuke %S Proceedings of the Fourth Workshop on Neural Generation and Translation %D 2020 %8 July %I Association for Computational Linguistics %C Online %F sharaf-etal-2020-meta %X 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). %R 10.18653/v1/2020.ngt-1.5 %U https://aclanthology.org/2020.ngt-1.5 %U https://doi.org/10.18653/v1/2020.ngt-1.5 %P 43-53