CUNI Submission for Low-Resource Languages in WMT News 2019
By Tom Kocmi, Ondrej Bojar. 2019
15 citations recorded by the source corpus.
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 a 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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ondrej Bojar
- Philipp Koehn
- Rico Sennrich
- Graham Neubig
- Felix Stahlberg
- Barry Haddow
- Matt Post
- Yonatan Belinkov
Citations in the corpus
- Findings of the 2019 Conference on Machine Translation (WMT19) (2019, background): “2.5.9 Charles University (CUNI) Systems CUNI-T2T-TRANSFER (Kocmi and Bojar, 2019) are Transformer neural machine translation systems (as implemented in Tensor2tensor) for Kazakh↔English, Gujarati↔English.”