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

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.

arXiv commentAccepted to EMNLP 2020 long paper

References in corpus (6)

• From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
• Does Neural Machine Translation Benefit from Larger Context?
• THUMT: An Open Source Toolkit for Neural Machine Translation
• Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches
• Context-Aware Learning for Neural Machine Translation
• Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language