Dual Learning for Machine Translation

TL;DR

This paper introduces dual-NMT, a reinforcement learning-based method that enables neural machine translation models to learn from unlabeled monolingual data by leveraging dual tasks, reducing reliance on costly bilingual datasets.

Contribution

The paper proposes a novel dual-learning mechanism for NMT that trains models using monolingual data through a dual task reinforcement learning framework, reducing the need for large bilingual datasets.

Findings

Dual-NMT achieves comparable accuracy to fully supervised models with only 10% bilingual data.

The dual-learning approach effectively utilizes monolingual data for translation training.

Experiments demonstrate strong performance on English-French translation tasks.

Abstract

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck, we develop a dual-learning mechanism, which can enable an NMT system to automatically learn from unlabeled data through a dual-learning game. This mechanism is inspired by the following observation: any machine translation task has a dual task, e.g., English-to-French translation (primal) versus French-to-English translation (dual); the primal and dual tasks can form a closed loop, and generate informative feedback signals to train the translation models, even if without the involvement of a human labeler. In the dual-learning mechanism, we use one agent to represent the model for the primal task and the other agent to represent the model for the dual task, then ask them to teach each other through a reinforcement learning process. Based on the feedback signals generated during this process (e.g., the language-model likelihood of the output of a model, and the reconstruction error of the original sentence after the primal and dual translations), we can iteratively update the two models until convergence (e.g., using the policy gradient methods). We call the corresponding approach to neural machine translation \emph{dual-NMT}. Experiments show that dual-NMT works very well on English$\leftrightarrow$French translation; especially, by learning from monolingual data (with 10% bilingual data for warm start), it achieves a comparable accuracy to NMT trained from the full bilingual data for the French-to-English translation task.