End-to-End Simultaneous Translation System for IWSLT2020 Using Modality Agnostic Meta-Learning

Hou Jeung Han, Mohd Abbas Zaidi, Sathish Reddy Indurthi, Nikhil Kumar Lakumarapu, Beomseok Lee, Sangha Kim


Abstract
In this paper, we describe end-to-end simultaneous speech-to-text and text-to-text translation systems submitted to IWSLT2020 online translation challenge. The systems are built by adding wait-k and meta-learning approaches to the Transformer architecture. The systems are evaluated on different latency regimes. The simultaneous text-to-text translation achieved a BLEU score of 26.38 compared to the competition baseline score of 14.17 on the low latency regime (Average latency ≤ 3). The simultaneous speech-to-text system improves the BLEU score by 7.7 points over the competition baseline for the low latency regime (Average Latency ≤ 1000).
Anthology ID:
2020.iwslt-1.5
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:
62–68
Language:
URL:
https://www.aclweb.org/anthology/2020.iwslt-1.5
DOI:
10.18653/v1/2020.iwslt-1.5
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.iwslt-1.5.pdf
Video:
 http://slideslive.com/38929597