@incollection{KrekGantarKosem2022,
  author    = {Krek, Simon and Gantar, Polona and Kosem, Iztok},
  title     = {Extraction of collocations from the Gigafida 2.1 corpus of Slovene},
  booktitle = {Dictionaries and Society. Proceedings of the XX EURALEX International Congress, 12-16 July 2022, Mannheim, Germany},
  editor    = {Klosa-K{\"u}ckelhaus, Annette and Engelberg, Stefan and M{\"o}hrs, Christine and Storjohann, Petra},
  isbn      = {978-3-937241-87-6},
  doi       = {10.14618/ids-pub-11182},
  url       = {https://euralex2022.ids-mannheim.de/wp-content/uploads/2022/07/Proceedings_11.07.2022.pdf},
  publisher      = {Leibniz-Institut f{\"u}r Deutsche Sprache (IDS)},
  pages     = {240 -- 252},
  year      = {2022},
  abstract  = {This paper describes a method for extracting collocation data from text corpora based on a formal definition of syntactic structures, which takes into account not only the POS-tagging level of annotation but also syntactic parsing (syntactic treebank model) and introduces the possibility of controlling the canonical form of extracted collocations based on statistical data on forms with different properties in the corpus. Specifically, we describe the results of extraction from the syntactically tagged Gigafida 2.1 corpus. Using the new method, 4,002,918 collocation candidates in 81 syntactic structures were extracted. We evaluate the extracted data sample in more detail, mainly in relation to properties that affect the extraction of canonical forms: definiteness in adjectival collocations, grammatical number in noun collocations, comparison in adjectival and adverbial collocations, and letter case (uppercase and lowercase) in canonical forms. The conclusion highlights the potential of the methodology used for the grammatical description of collocation and phrasal syntax and the possibilities for improving the model in the process of compilation of a digital dictionary database for Slovene.},
  subject      = {Korpus <Linguistik>},
  language  = {en}
}