CUNI Submission for Low-Resource Languages in WMT News 2019
Tom Kocmi, Ondřej Bojar · 2019
This paper describes the CUNI submission to the WMT 2019 News Translation Shared Task for the low-resource languages: Gujarati-English and Kazakh-English.We participated in both language pairs in both translation directions.Our system combines transfer learning from different high-resource language pair followed by training on backtranslated monolingual data.Thanks to the simultaneous training in both directions, we can iterate the backtranslation process.We are using the Transformer model in a constrained submission.