BIT’s system for the AutoSimTrans 2020

Minqin Li, Haodong Cheng, Yuanjie Wang, Sijia Zhang, Liting Wu, Yuhang Guo


Abstract
This paper describes our machine translation systems for the streaming Chinese-to-English translation task of AutoSimTrans 2020. We present a sentence length based method and a sentence boundary detection model based method for the streaming input segmentation. Experimental results of the transcription and the ASR output translation on the development data sets show that the translation system with the detection model based method outperforms the one with the length based method in BLEU score by 1.19 and 0.99 respectively under similar or better latency.
Anthology ID:
2020.autosimtrans-1.6
Volume:
Proceedings of the First Workshop on Automatic Simultaneous Translation
Month:
July
Year:
2020
Address:
Seattle, Washington
Editors:
Hua Wu, Colin Cherry, Liang Huang, Zhongjun He, Mark Liberman, James Cross, Yang Liu
Venue:
AutoSimTrans
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
37–44
Language:
URL:
https://aclanthology.org/2020.autosimtrans-1.6
DOI:
10.18653/v1/2020.autosimtrans-1.6
Bibkey:
Cite (ACL):
Minqin Li, Haodong Cheng, Yuanjie Wang, Sijia Zhang, Liting Wu, and Yuhang Guo. 2020. BIT’s system for the AutoSimTrans 2020. In Proceedings of the First Workshop on Automatic Simultaneous Translation, pages 37–44, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
BIT’s system for the AutoSimTrans 2020 (Li et al., AutoSimTrans 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.autosimtrans-1.6.pdf
Video:
 http://slideslive.com/38929922