Simultaneous Translation Policies: From Fixed to Adaptive

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


Abstract
Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous methods on obtaining adaptive policies either rely on complicated training process, or underperform simple fixed policies. We design an algorithm to achieve adaptive policies via a simple heuristic composition of a set of fixed policies. Experiments on Chinese -> English and German -> English show that our adaptive policies can outperform fixed ones by up to 4 BLEU points for the same latency, and more surprisingly, it even surpasses the BLEU score of full-sentence translation in the greedy mode (and very close to beam mode), but with much lower latency.
Anthology ID:
2020.acl-main.254
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:
2847–2853
Language:
URL:
https://aclanthology.org/2020.acl-main.254
DOI:
10.18653/v1/2020.acl-main.254
Bibkey:
Cite (ACL):
Baigong Zheng, Kaibo Liu, Renjie Zheng, Mingbo Ma, Hairong Liu, and Liang Huang. 2020. Simultaneous Translation Policies: From Fixed to Adaptive. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2847–2853, Online. Association for Computational Linguistics.
Cite (Informal):
Simultaneous Translation Policies: From Fixed to Adaptive (Zheng et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.acl-main.254.pdf
Video:
 http://slideslive.com/38928934