NAIST’s Machine Translation Systems for IWSLT 2020 Conversational Speech Translation Task

Ryo Fukuda, Katsuhito Sudoh, Satoshi Nakamura


Abstract
This paper describes NAIST’s NMT system submitted to the IWSLT 2020 conversational speech translation task. We focus on the translation disfluent speech transcripts that include ASR errors and non-grammatical utterances. We tried a domain adaptation method by transferring the styles of out-of-domain data (United Nations Parallel Corpus) to be like in-domain data (Fisher transcripts). Our system results showed that the NMT model with domain adaptation outperformed a baseline. In addition, slight improvement by the style transfer was observed.
Anthology ID:
2020.iwslt-1.21
Volume:
Proceedings of the 17th International Conference on Spoken Language Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Marcello Federico, Alex Waibel, Kevin Knight, Satoshi Nakamura, Hermann Ney, Jan Niehues, Sebastian Stüker, Dekai Wu, Joseph Mariani, Francois Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
172–177
Language:
URL:
https://aclanthology.org/2020.iwslt-1.21
DOI:
10.18653/v1/2020.iwslt-1.21
Bibkey:
Cite (ACL):
Ryo Fukuda, Katsuhito Sudoh, and Satoshi Nakamura. 2020. NAIST’s Machine Translation Systems for IWSLT 2020 Conversational Speech Translation Task. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 172–177, Online. Association for Computational Linguistics.
Cite (Informal):
NAIST’s Machine Translation Systems for IWSLT 2020 Conversational Speech Translation Task (Fukuda et al., IWSLT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwslt-1.21.pdf