papers AI Learner
The Github is limit! Click to go to the new site.

Curriculum Learning for Domain Adaptation in Neural Machine Translation

2019-05-14
Xuan Zhang, Pamela Shapiro, Gaurav Kumar, Paul McNamee, Marine Carpuat, Kevin Duh

Abstract

We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the training algorithm with a particular schedule. This approach is simple to implement on top of any neural framework or architecture, and consistently outperforms both unadapted and adapted baselines in experiments with two distinct domains and two language pairs.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.05816

PDF

http://arxiv.org/pdf/1905.05816


Comments

Content