The University of Maryland’s Kazakh-English Neural Machine Translation System at WMT19

By Eleftheria Briakou, Marine Carpuat. 2019

15 citations recorded by the source corpus.

This paper describes the University of Maryland’s submission to the WMT 2019 Kazakh-English news translation task. We study the impact of transfer learning from another low-resource but related language. We experiment with different ways of encoding lexical units to maximize lexical overlap between the two language pairs, as well as back-translation and ensembling. The submitted system improves over a Kazakh-only baseline by +5.45 BLEU on newstest2019.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

Citations in the corpus

• Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution (2021, neutral): “5 Casas et al. (2019) 15.”
• Findings of the 2019 Conference on Machine Translation (WMT19) (2019, neutral): “45 UMD (Briakou and Carpuat, 2019)”