TY - GEN
T1 - An empirical study on task-oriented dialogue translation
AU - Liu, Siyou
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - 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
AB - 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
KW - Discourse
KW - Multilingual
KW - Neural Machine Translation
KW - Pre-Training
KW - Task-Oriented Dialogue
UR - https://www.scopus.com/pages/publications/85115068633
U2 - 10.1109/ICASSP39728.2021.9413521
DO - 10.1109/ICASSP39728.2021.9413521
M3 - Conference contribution
AN - SCOPUS:85115068633
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 7558
EP - 7562
BT - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
Y2 - 6 June 2021 through 11 June 2021
ER -