
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.
Research Areas
Authored Publications
Sort By
Google
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
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
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