log in  |  register  |  feedback?  |  help  |  web accessibility
Meta-Learning for Few-Shot NMT Adaptation.
Wednesday, February 5, 2020, 11:00 am-12:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)

In this talk I'll 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).


Amr Sharaf is a PhD candidate in the Computational Linguistics and Information Processing (CLIP) Lab at the University of Maryland, advised by Hal Daumé III. His research focuses on developing meta-learning algorithms in the context of structured prediction for AI and NLP. He is interested in applying reinforcement and imitation learning algorithms for meta-learning and structured prediction problems in weakly supervised settings.

This talk is organized by Doug Oard