The first neural machine translation system for the Erzya language

FieldMatters (COLING) 2022  ·  David Dale ·

We present the first neural machine translation system for translation between the endangered Erzya language and Russian and the dataset collected by us to train and evaluate it. The BLEU scores are 17 and 19 for translation to Erzya and Russian respectively, and more than half of the translations are rated as acceptable by native speakers. We also adapt our model to translate between Erzya and 10 other languages, but without additional parallel data, the quality on these directions remains low. We release the translation models along with the collected text corpus, a new language identification model, and a multilingual sentence encoder adapted for the Erzya language. These resources will be available at

PDF Abstract FieldMatters (COLING) 2022 PDF FieldMatters (COLING) 2022 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Machine Translation slone/myv_ru_2022 myv-ru slone/mbart-large-51-myv-mul-v1 ChrF++ 38.63 # 1
Machine Translation slone/myv_ru_2022 ru-myv slone/mbart-large-51-mul-myv-v1 ChrF++ 41.16 # 1


No methods listed for this paper. Add relevant methods here