@inproceedings{coltekin-etal-2026-tokenisation,
    title = "Tokenisation of {T}urkic Copula Constructions in {U}niversal {D}ependencies",
    author = "Coltekin, Cagri  and
      Akkurt, Furkan  and
      Chontaeva, Bermet  and
      Eslami, Soudabeh  and
      Ivanova, Sardana  and
      Dzhumalieva, Gulnura  and
      Kasieva, Aida  and
      Mus, Nikolett  and
      Washington, Jonathan",
    editor = {Oflazer, Kemal  and
      K{\"o}ksal, Abdullatif  and
      Varol, Onur},
    booktitle = "Proceedings of the Second Workshop Natural Language Processing for {T}urkic Languages ({SIGTURK} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.sigturk-1.14/",
    pages = "172--178",
    ISBN = "979-8-89176-370-8",
    abstract = "Identifying units, `syntactic words', for morphosyntactic analysis is important yet challenging for morphologically rich languages. In this paper we propose a set of guiding principles to determine units of morphosyntactic analysis, and apply them to the case of copular constructions in Turkic languages, in the context of Universal Dependencies (UD) framework. We also provide a survey of the practice in the Turkic UD treebanks published to date, and discuss the advantages and disadvantages of the proposed tokenisation for a selection of Turkic languages."
}