@inproceedings{beyer-frassinelli-2025-linguistic,
    title = "Linguistic Features in {G}erman {BERT}: The Role of Morphology, Syntax, and Semantics in Multi-Class Text Classification",
    author = "Beyer, Henrike  and
      Frassinelli, Diego",
    editor = "Ebrahimi, Abteen  and
      Haider, Samar  and
      Liu, Emmy  and
      Haider, Sammar  and
      Leonor Pacheco, Maria  and
      Wein, Shira",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
    month = apr,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.naacl-srw.3/",
    doi = "10.18653/v1/2025.naacl-srw.3",
    pages = "28--39",
    ISBN = "979-8-89176-192-6",
    abstract = {Most studies on the linguistic information encoded by BERT primarily focus on English. Our study examines a monolingual German BERT model using a semantic classification task on newspaper articles, analysing the linguistic features influencing classification decisions through SHAP values. We use the T{\"u}Ba-D/Z corpus, a resource with gold-standard annotations for a set of linguistic features, including POS, inflectional morphology, phrasal, clausal, and dependency structures. Semantic features of nouns are evaluated via the GermaNet ontology using shared hypernyms. Our results indicate that the features identified in English also affect classification in German but suggests important language- and task-specific features as well.}
}