Publication at Faculty of Mathematics and Physics |
2021
Abstract
We present our submissions to the WMT21 shared task in Unsupervised and Very Low-Resource machine translation between German and Upper Sorbian, German and Lower Sorbian, and Russian and Chuvash. Our low-resource systems (GermanLEFT RIGHT ARROW Upper Sorbian, RussianLEFT RIGHT ARROW Chuvash) are pre-trained on high-resource pairs of related languages.
We fine-tune those systems using the available authentic parallel data and improve by iterated back-translation. The unsupervised GermanLEFT RIGHT ARROW Lower Sorbian system is initialized by the best Upper Sorbian system and improved by iterated back-translation using monolingual data only.