Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021

Katsuki Chousa, Makoto Morishita


Abstract
This paper describes our systems that were submitted to the restricted translation task at WAT 2021. In this task, the systems are required to output translated sentences that contain all given word constraints. Our system combined input augmentation and constrained beam search algorithms. Through experiments, we found that this combination significantly improves translation accuracy and can save inference time while containing all the constraints in the output. For both En->Ja and Ja->En, our systems obtained the best evaluation performances in automatic and human evaluation.
Anthology ID:
2021.wat-1.3
Volume:
Proceedings of the 8th Workshop on Asian Translation (WAT2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
53–61
Language:
URL:
https://aclanthology.org/2021.wat-1.3
DOI:
10.18653/v1/2021.wat-1.3
Bibkey:
Cite (ACL):
Katsuki Chousa and Makoto Morishita. 2021. Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 53–61, Online. Association for Computational Linguistics.
Cite (Informal):
Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021 (Chousa & Morishita, WAT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wat-1.3.pdf
Data
ASPEC