Reinforcement Learning based Curriculum Optimization for Neural Machine Translation

Understand

We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT).

• Specifically, given a training dataset with a sentence-level feature such as noise, we seek an optimal curriculum, or order for presenting examples to the system during training.
• Our curriculum framework allows examples to appear an arbitrary number of times, and thus generalizes data weighting, filtering, and fine-tuning schemes.
• Rather than relying on prior knowledge to design a curriculum, we use reinforcement learning to learn one automatically, jointly with the NMT system, in the course of a single training run.