@inproceedings{stephen-libovicky-2026-evaluating,
    title = "Evaluating Morphological Plausibility of Subword Tokenization via Statistical Alignment with Morpho-Syntactic Features",
    author = "Stephen, Abishek  and
      Libovick{\'y}, Jind{\v{r}}ich",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.196/",
    pages = "3783--3791",
    ISBN = "979-8-89176-386-9",
    abstract = "We present a novel metric for the evaluation of morphological plausibility of subword segmentation.Unlike the typically used morpheme boundary or retrieval F-score, which requires gold segmentation data that is either unavailable or of inconsistent quality across many languages, our approach utilizes morpho-syntactic features.These are available in resources such as Universal Dependencies or UniMorph for a much wider range of languages.The metric works by probabilistically aligning subwords with morphological features through an IBM Model 1.Our experiments show that the metric correlates well with traditional morpheme boundary recall while being more broadly applicable across languages with different morphological systems."
}