Towards decoding as continuous optimisation in neural machine translation

Cong Duy Vu Hoang, Gholamreza Haffari, Trevor Cohn

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

    Abstract

    We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We reformulate decoding, a discrete optimization problem, into a continuous problem, such that optimization can make use of efficient gradient-based techniques. Our powerful decoding framework allows for more accurate decoding for standard neural machine
    translation models, as well as enabling decoding in intractable models such
    as intersection of several different NMT models. Our empirical results show that
    our decoding framework is effective, and can leads to substantial improvements in translations, especially in situations where greedy search and beam search are not feasible. Finally, we show how the technique is highly competitive with, and complementary
    to, reranking
    Original languageEnglish
    Title of host publicationThe Conference on Empirical Methods in Natural Language Processing
    Subtitle of host publicationProceedings of the Conference - September 9-11, 2017, Copenhagen, Denmark
    EditorsRebecca Hwa, Sebastian Riedel
    Place of PublicationStroudsburg PA USA
    PublisherAssociation for Computational Linguistics (ACL)
    Pages146-156
    Number of pages11
    ISBN (Print)9781945626838
    DOIs
    Publication statusPublished - 2017
    EventEmpirical Methods in Natural Language Processing 2017 - Copenhagen, Denmark
    Duration: 9 Sep 201711 Sep 2017
    http://www.aclweb.org/anthology/D/D17/

    Conference

    ConferenceEmpirical Methods in Natural Language Processing 2017
    Abbreviated titleEMNLP 2017
    CountryDenmark
    CityCopenhagen
    Period9/09/1711/09/17
    Internet address

    Cite this

    Hoang, C. D. V., Haffari, G., & Cohn, T. (2017). Towards decoding as continuous optimisation in neural machine translation. In R. Hwa, & S. Riedel (Eds.), The Conference on Empirical Methods in Natural Language Processing: Proceedings of the Conference - September 9-11, 2017, Copenhagen, Denmark (pp. 146-156). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/D17-1014