Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation

Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Stephan Vogel


Abstract
We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU loss and Average Proportion (AP) constraint. Our agent outperforms previously proposed Wait-if-diff and Wait-if-worse agents (Cho and Esipova, 2016) on BLEU with a lower latency. Secondly we proposed data-driven changes to Neural MT training to better match the incremental decoding framework.
Anthology ID:
N18-2079
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
493–499
Language:
URL:
https://aclanthology.org/N18-2079
DOI:
10.18653/v1/N18-2079
Bibkey:
Cite (ACL):
Fahim Dalvi, Nadir Durrani, Hassan Sajjad, and Stephan Vogel. 2018. Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 493–499, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation (Dalvi et al., NAACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/N18-2079.pdf
Note:
 N18-2079.Notes.pdf