Prediction Improves Simultaneous Neural Machine Translation

Ashkan Alinejad, Maryam Siahbani, Anoop Sarkar


Abstract
Simultaneous speech translation aims to maintain translation quality while minimizing the delay between reading input and incrementally producing the output. We propose a new general-purpose prediction action which predicts future words in the input to improve quality and minimize delay in simultaneous translation. We train this agent using reinforcement learning with a novel reward function. Our agent with prediction has better translation quality and less delay compared to an agent-based simultaneous translation system without prediction.
Anthology ID:
D18-1337
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3022–3027
Language:
URL:
https://aclanthology.org/D18-1337
DOI:
10.18653/v1/D18-1337
Bibkey:
Cite (ACL):
Ashkan Alinejad, Maryam Siahbani, and Anoop Sarkar. 2018. Prediction Improves Simultaneous Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3022–3027, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Prediction Improves Simultaneous Neural Machine Translation (Alinejad et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/D18-1337.pdf
Attachment:
 D18-1337.Attachment.zip