An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models

Varun Gumma, Raj Dabre, Pratyush Kumar. An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models. In Mary Nurminen, Judith Brenner, Maarit Koponen, Sirkku Latomaa, Mikhail Mikhailov, Frederike Schierl, Tharindu Ranasinghe, Eva Vanmassenhove, Sergi Alvarez Vidal, Nora Aranberri, Mara Nunziatini, Carla Parra Escartín, Mikel L. Forcada, Maja Popovic, Carolina Scarton, Helena Moniz, editors, Proceedings of the 24th Annual Conference of the European Association for Machine Translation, EAMT 2023, Tampere, Finland, 12-15 June 2023. pages 103-114, European Association for Machine Translation, 2023. [doi]

@inproceedings{GummaDK23,
  title = {An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models},
  author = {Varun Gumma and Raj Dabre and Pratyush Kumar},
  year = {2023},
  url = {https://aclanthology.org/2023.eamt-1.11},
  researchr = {https://researchr.org/publication/GummaDK23},
  cites = {0},
  citedby = {0},
  pages = {103-114},
  booktitle = {Proceedings of the 24th Annual Conference of the European Association for Machine Translation, EAMT 2023, Tampere, Finland, 12-15 June 2023},
  editor = {Mary Nurminen and Judith Brenner and Maarit Koponen and Sirkku Latomaa and Mikhail Mikhailov and Frederike Schierl and Tharindu Ranasinghe and Eva Vanmassenhove and Sergi Alvarez Vidal and Nora Aranberri and Mara Nunziatini and Carla Parra Escartín and Mikel L. Forcada and Maja Popovic and Carolina Scarton and Helena Moniz},
  publisher = {European Association for Machine Translation},
  isbn = {978-952-03-2947-1},
}