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
- 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)
- PDF:
- https://preview.aclanthology.org/fix_video/2020.ngt-1.5.pdf