2021/09/24 by Lukas Edman, Edman, Lukas, Ahmet Üstün +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2109.12012
openalex publication_date 2021/09/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German--Lower Sorbian (DE--DSB): a high-resource language to a low-resource one. Our system uses a transformer encoder-decoder architecture in which we make three changes to the standard training procedure. First, our training focuses on two languages at a time, contrasting with a wealth of research on multilingual systems. Second, we introduce a novel method for initializing the vocabulary of an unseen language, achieving improvements of 3.2 BLEU for DE→DSB and 4.0 BLEU for DSB→DE. Lastly, we experiment with the order in which offline and online back-translation are used to train an unsupervised system, finding that using online back-translation first works better for DE→DSB by 2.76 BLEU. Our submissions ranked first (tied with another team) for DSB→DE and third for DE→DSB.