An empirical study on task-oriented dialogue translation

Siyou Liu

Research output: Contribution to journalConference articlepeer-review


Translating conversational text, in particular task-oriented dialogues, is an important application task for machine translation technology. However, it has so far not been extensively explored due to its inherent characteristics including data limitation, discourse, informality and personality. In this paper, we systematically investigate advanced models on the task-oriented dialogue translation task, including sentence-level, document-level and non-autoregressive NMT models. Besides, we explore existing techniques such as data selection, back/forward translation, larger batch learning, finetuning and domain adaptation. To alleviate low-resource problem, we transfer general knowledge from four different pre-training models to the downstream task. Encouragingly, we find that the best model with mBART pre-training pushes the SOTA performance on WMT20 English-German and IWSLT DIALOG Chinese-English datasets up to 62.67 and 23.21 BLEU points, respectively.1

Original languageEnglish
Pages (from-to)7558-7562
Number of pages5
JournalProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Publication statusPublished - 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 6 Jun 202111 Jun 2021


  • Discourse
  • Multilingual
  • Neural Machine Translation
  • Pre-Training
  • Task-Oriented Dialogue


Dive into the research topics of 'An empirical study on task-oriented dialogue translation'. Together they form a unique fingerprint.

Cite this