@inproceedings{otmakhova-etal-2022-cross,
    title = "Cross-linguistic Comparison of Linguistic Feature Encoding in {BERT} Models for Typologically Different Languages",
    author = "Otmakhova, Yulia  and
      Verspoor, Karin  and
      Lau, Jey Han",
    editor = "Vylomova, Ekaterina  and
      Ponti, Edoardo  and
      Cotterell, Ryan",
    booktitle = "Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
    month = jul,
    year = "2022",
    address = "Seattle, Washington",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.sigtyp-1.4/",
    doi = "10.18653/v1/2022.sigtyp-1.4",
    pages = "27--35",
    abstract = "Though recently there have been an increased interest in how pre-trained language models encode different linguistic features, there is still a lack of systematic comparison between languages with different morphology and syntax. In this paper, using BERT as an example of a pre-trained model, we compare how three typologically different languages (English, Korean, and Russian) encode morphology and syntax features across different layers. In particular, we contrast languages which differ in a particular aspect, such as flexibility of word order, head directionality, morphological type, presence of grammatical gender, and morphological richness, across four different tasks."
}