Abstract
This paper describes the joint submission to the IWSLT 2018 Low Resource MT task by Samsung R&D Institute, Poland, and the University of Edinburgh. We focused on supplementing the very limited in-domain Basque-English training data with out-of-domain data, with synthetic data, and with data for other language pairs. We also experimented with a variety of model architectures and features, which included the development of extensions to the Nematus toolkit. Our submission was ultimately produced by a system combination in which we reranked translations from our strongest individual system using multiple weaker systems.
Original language | English |
---|---|
Title of host publication | Proceedings of the 15th International Workshop on Spoken Language Translation |
Place of Publication | Bruges, Belgium |
Pages | 118-123 |
Number of pages | 6 |
Publication status | Published - 2018 |
Event | 15th International Workshop on Spoken Language Translation 2018 - Bruges, Belgium Duration: 29 Oct 2018 → 30 Oct 2018 https://workshop2018.iwslt.org/index.php |
Conference
Conference | 15th International Workshop on Spoken Language Translation 2018 |
---|---|
Abbreviated title | IWSLT 2018 |
Country/Territory | Belgium |
City | Bruges |
Period | 29/10/18 → 30/10/18 |
Internet address |