Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020

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

    3 Downloads (Pure)

    Abstract

    This paper describes our submission for the English-Tamil news translation task of WMT-2020. The various techniques and Neural Machine Translation (NMT) models used by our team are presented and discussed, including back-translation, fine-tuning and word dropout. Additionally, our experiments show that using a linguistically motivated subword segmentation technique (Ataman et al., 2017) does not consistently outperform the more widely used, non-linguistically motivated SentencePiece algorithm (Kudo and Richardson, 2018), despite the agglutinative nature of Tamil morphology.
    Original languageEnglish
    Title of host publicationProceedings of the 5th Conference on Machine Translation (WMT)
    EditorsLoïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Yvette Graham, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri
    PublisherAssociation for Computational Linguistics (ACL)
    Pages126-133
    Number of pages8
    Publication statusPublished - Nov-2020

    Cite this