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
- URL:
- https://www.aclweb.org/anthology/2020.iwslt-1.5
- DOI:
- PDF:
- https://www.aclweb.org/anthology/2020.iwslt-1.5.pdf
You can write comments here (and agree to place them under CC-by). They are not guaranteed to stay and there is no e-mail functionality.