A Survey on Document-level Neural Machine Translation: Methods and Evaluation

Machine translation (MT) is an important task in natural language processing (NLP), as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality surpasses that of the translations obtained using statistical techniques for most language-pairs. Up until a few years ago, almost all of the neural translation models translated sentences independently, without incorporating the wider document context and inter-dependencies among the sentences. The aim of this survey article is to highlight the major works that have been undertaken in the space of document-level machine translation after the neural revolution, so researchers can recognize the current state and future directions of this field We provide an organization of the literature based on novelties in modelling and architectures as well as training and decoding strategies. In addition, we cover evaluation strategies that have been introduced to account for the improvements in document MT, including automatic metrics and discourse-targeted test sets. We conclude by presenting possible avenues for future exploration in this research field.

Automated summary

Machine translation is a vital task in natural language processing that automates the translation process and decreases reliance on human translators. With the advancement of neural networks, translation quality has improved, surpassing that of statistical techniques. This survey article focuses on the advancements in document-level machine translation post-neural revolution, highlighting the current state and future directions of the field.