Simultaneous Neural Machine Translation with Constituent Label Prediction

Yasumasa Kano, Katsuhito Sudoh, Satoshi Nakamura


Abstract
Simultaneous translation is a task in which translation begins before the speaker has finished speaking, so it is important to decide when to start the translation process. However, deciding whether to read more input words or start to translate is difficult for language pairs with different word orders such as English and Japanese. Motivated by the concept of pre-reordering, we propose a couple of simple decision rules using the label of the next constituent predicted by incremental constituent label prediction. In experiments on English-to-Japanese simultaneous translation, the proposed method outperformed baselines in the quality-latency trade-off.
Anthology ID:
2021.wmt-1.120
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Editors:
Loic Barrault, Ondrej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussa, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Tom Kocmi, Andre Martins, Makoto Morishita, Christof Monz
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1124–1134
Language:
URL:
https://aclanthology.org/2021.wmt-1.120
DOI:
Bibkey:
Cite (ACL):
Yasumasa Kano, Katsuhito Sudoh, and Satoshi Nakamura. 2021. Simultaneous Neural Machine Translation with Constituent Label Prediction. In Proceedings of the Sixth Conference on Machine Translation, pages 1124–1134, Online. Association for Computational Linguistics.
Cite (Informal):
Simultaneous Neural Machine Translation with Constituent Label Prediction (Kano et al., WMT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wmt-1.120.pdf
Video:
 https://aclanthology.org/2021.wmt-1.120.mp4