Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based method for dynamically selecting context sentences in document-level neural machine translation, leading to improved translation quality by adapting context scope to individual source sentences.

Contribution

It proposes a novel context selection module trained with reinforcement learning to adaptively choose relevant context sentences for each source sentence in document translation.

Findings

Significantly improves translation performance over fixed context methods

Effectively selects relevant context sentences for different source sentences

End-to-end training with a novel reward enhances context utilization

Abstract

Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different sizes of context. To address this problem, we propose an effective approach to select dynamic context so that the document-level translation model can utilize the more useful selected context sentences to produce better translations. Specifically, we introduce a selection module that is independent of the translation module to score each candidate context sentence. Then, we propose two strategies to explicitly select a variable number of context sentences and feed them into the translation module. We train the two modules end-to-end via reinforcement learning. A novel reward is proposed to encourage the selection and utilization of dynamic context sentences. Experiments demonstrate that our approach can select adaptive context sentences for different source sentences, and significantly improves the performance of document-level translation methods.