ACLFeb, 2021

面向个性化及文档级对话机器翻译

TL;DRPersonalised NMT and document-level NMT are proposed to incorporate extra-textual information directly into the machine translation process, with the aim of improving the accuracy of translation for subtitles in five languages, respectively. The main challenges are addressed by incorporating extra-textual information, improving the accuracy of cohesion devices, and proposing reliable evaluation metrics for PersNMT and DocNMT.