On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss

Liu, Yihong; Chronopoulou, Alexandra; Schütze, Hinrich and Fraser, Alexander (July 2023): On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss. 20th International Conference on Spoken Language Translation (IWSLT 2023), Toronto, Canada, July 13 - 14, 2023. Salesky, Elizabeth; Federico, Marcello and Carpuat, Marine (eds.) : In: Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), Stroudsburg, PA: Association for Computational Linguistics (ACL). pp. 491-502

Abstract

Although unsupervised neural machine translation (UNMT) has achieved success in many language pairs, the copying problem, i.e., directly copying some parts of the input sentence as the translation, is common among distant language pairs, especially when low-resource languages are involved. We find this issue is closely related to an unexpected copying behavior during online back-translation (BT). In this work, we propose a simple but effective training schedule that incorporates a language discriminator loss. The loss imposes constraints on the intermediate translation so that the translation is in the desired language. By conducting extensive experiments on different language pairs, including similar and distant, high and low-resource languages, we find that our method alleviates the copying problem, thus improving the translation performance on low-resource languages.

• Item Type: Conference or Workshop Item (Paper)
• EU Funded Grant Agreement Number: 740516
• EU Projects: Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement
• Research Centers: Center for Information and Language Processing (CIS)
• Subjects: 400 Language > 400 Language; 400 Language > 410 Linguistics
• Place of Publication: Stroudsburg, PA
• Annotation: ISBN 978-1-959429-84-5
• Language: English