David Vilar

David Vilar

David Vilar is a Research Scientist working for Google Translate since 2020. He has been working on machine translation research since 2003, and was co-author of the open source Jane (developed by RWTH Aachen) and Sockeye (developed by Amazon) systems.
Authored Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Prompting PaLM for Translation: Assessing Strategies and Performance
    Jiaming Luo
    Viresh Ratnakar
    George Foster
    Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Toronto, Canada (2023), 15406–15427
    There's no Data Like Better Data: Using QE Metrics for MT Data Filtering
    Jan-Thorsten Peter
    Mara Finkelstein
    Jurik Juraska
    Proceedings of the Eighth Conference on Machine Translation, Association for Computational Linguistics, Singapore (2023), pp. 561-577
    A Natural Diet: Towards Improving Naturalness of Machine Translation Output
    David Grangier
    George Foster
    Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Online (2022)
    Controlling Machine Translation for Multiple Aspects with Additive Interventions
    Andrea Schioppa
    Artem Sokolov
    Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, pp. 6676-6696