Curriculum Learning for Domain Adaptation in Neural Machine Translation
This addresses the problem of adapting generic translation models to specific domains for users needing specialized translations, but it is incremental as it builds on existing curriculum learning methods.
The paper tackles domain adaptation in neural machine translation by introducing a curriculum learning approach that groups samples by similarity to the target domain and trains them on a schedule, resulting in consistent outperformance of baselines across two domains and language pairs.
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.