Opportunistic Decoding with Timely Correction for Simultaneous Translation

Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Liang Huang


Abstract
Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently. Most existing frameworks, however, have difficulties in balancing between the translation quality and latency, i.e., the decoding policy is usually either too aggressive or too conservative. We propose an opportunistic decoding technique with timely correction ability, which always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information. At the same time, it also corrects, in a timely fashion, the mistakes in the former overgenerated words when observing more source context to ensure high translation quality. Experiments show our technique achieves substantial reduction in latency and up to +3.1 increase in BLEU, with revision rate under 8% in Chinese-to-English and English-to-Chinese translation.
Anthology ID:
2020.acl-main.42
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
437–442
Language:
URL:
https://aclanthology.org/2020.acl-main.42
DOI:
10.18653/v1/2020.acl-main.42
Bibkey:
Cite (ACL):
Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, and Liang Huang. 2020. Opportunistic Decoding with Timely Correction for Simultaneous Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 437–442, Online. Association for Computational Linguistics.
Cite (Informal):
Opportunistic Decoding with Timely Correction for Simultaneous Translation (Zheng et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.42.pdf
Video:
 http://slideslive.com/38929355