@inproceedings{singh-lefever-2022-student,
    title = "When the Student Becomes the Master: Learning Better and Smaller Monolingual Models from m{BERT}",
    author = "Singh, Pranaydeep  and
      Lefever, Els",
    editor = "Calzolari, Nicoletta  and
      Huang, Chu-Ren  and
      Kim, Hansaem  and
      Pustejovsky, James  and
      Wanner, Leo  and
      Choi, Key-Sun  and
      Ryu, Pum-Mo  and
      Chen, Hsin-Hsi  and
      Donatelli, Lucia  and
      Ji, Heng  and
      Kurohashi, Sadao  and
      Paggio, Patrizia  and
      Xue, Nianwen  and
      Kim, Seokhwan  and
      Hahm, Younggyun  and
      He, Zhong  and
      Lee, Tony Kyungil  and
      Santus, Enrico  and
      Bond, Francis  and
      Na, Seung-Hoon",
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.coling-1.391/",
    pages = "4434--4441",
    abstract = "In this research, we present pilot experiments to distil monolingual models from a jointly trained model for 102 languages (mBERT). We demonstrate that it is possible for the target language to outperform the original model, even with a basic distillation setup. We evaluate our methodology for 6 languages with varying amounts of resources and language families."
}