Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System
Pinzhen Chen, Nikolay Bogoychev, Ulrich Germann
Abstract
This paper describes the University of Edinburgh’s neural machine translation systems submitted to the IWSLT 2020 open domain Japanese↔Chinese translation task. On top of commonplace techniques like tokenisation and corpus cleaning, we explore character mapping and unsupervised decoding-time adaptation. Our techniques focus on leveraging the provided data, and we show the positive impact of each technique through the gradual improvement of BLEU.- Anthology ID:
- 2020.iwslt-1.14
- 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:
- 122–129
- URL:
- https://www.aclweb.org/anthology/2020.iwslt-1.14
- DOI:
- PDF:
- https://www.aclweb.org/anthology/2020.iwslt-1.14.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.