Meta-Learning for Few-Shot NMT Adaptation
This addresses the challenge of domain adaptation for machine translation practitioners, but it is incremental as it builds on existing meta-learning and NMT methods.
The paper tackles the problem of adapting neural machine translation systems to new domains with minimal data, showing that META-MT outperforms classical fine-tuning by up to 2.5 BLEU points using only 4,000 translated words.
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 domains 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).