@inproceedings{keles-etal-2025-cognate,
    title = "Cognate and Contact-Induced Transfer Learning for Hamshentsnag: A Low-Resource and Endangered Language",
    author = {Kele{\c{s}}, Onur  and
      G{\"u}nay, Baran  and
      Do{\u{g}}an, Berat},
    editor = "Nguyen, Duc",
    booktitle = "Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.lm4uc-1.9/",
    pages = "76--85",
    ISBN = "979-8-89176-242-8",
    abstract = "This study investigates zero-shot and few-shot cross-lingual transfer effects in Part-of-Speech (POS) tagging and Named Entity Recognition (NER) for Hamshentsnag, an endangered Western Armenian dialect. We examine how different source languages, Western Armenian (contact cognate), Eastern Armenian (ancestral cognate), Turkish (substrate or contact-induced), and English (non-cognate), affect the task performance using multilingual BERT and BERTurk. Results show that cognate varieties improved POS tagging by 8{\%} F1, while the substrate source enhanced NER by 15{\%} F1. BERTurk outperformed mBERT on NER but not on POS. We attribute this to task-specific advantages of different source languages. We also used script conversion and phonetic alignment with the target for non-Latin scripts, which alleviated transfer."
}