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
Venues:
ACL | IWSLT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
172–177
Language:
URL:
https://www.aclweb.org/anthology/2020.iwslt-1.21
DOI:
10.18653/v1/2020.iwslt-1.21
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.iwslt-1.21.pdf