Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language

Lukas Edman, Ahmet Üstün, Antonio Toral Ruiz, Gertjan van Noord

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    6 Citations (Scopus)
    19 Downloads (Pure)

    Abstract

    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.
    Original languageEnglish
    Title of host publicationProceedings of the Sixth Conference on Machine Translation
    PublisherAssociation for Computational Linguistics (ACL)
    Pages982-988
    Number of pages7
    Publication statusPublished - 2021
    EventSixth Conference on Machine Translation - Online
    Duration: 10-Nov-202111-Nov-2021

    Conference

    ConferenceSixth Conference on Machine Translation
    Period10/11/202111/11/2021

    Cite this