Leveraging Discourse Rewards for Document-Level Neural Machine Translation
This work addresses the challenge of producing cohesive and coherent translations for document-level machine translation, which is incremental as it builds on existing discourse metrics and reinforcement learning techniques.
The paper tackled the problem of document-level machine translation lacking explicit discourse quality optimization by proposing a reinforcement learning approach that optimizes lexical cohesion and coherence metrics, achieving improvements of up to 2.46 pp in lexical cohesion and 1.17 pp in coherence over competitive methods while maintaining translation faithfulness.
Document-level machine translation focuses on the translation of entire documents from a source to a target language. It is widely regarded as a challenging task since the translation of the individual sentences in the document needs to retain aspects of the discourse at document level. However, document-level translation models are usually not trained to explicitly ensure discourse quality. Therefore, in this paper we propose a training approach that explicitly optimizes two established discourse metrics, lexical cohesion (LC) and coherence (COH), by using a reinforcement learning objective. Experiments over four different language pairs and three translation domains have shown that our training approach has been able to achieve more cohesive and coherent document translations than other competitive approaches, yet without compromising the faithfulness to the reference translation. In the case of the Zh-En language pair, our method has achieved an improvement of 2.46 percentage points (pp) in LC and 1.17 pp in COH over the runner-up, while at the same time improving 0.63 pp in BLEU score and 0.47 pp in F_BERT.