@inproceedings{buljan-snajder-2017-combining,
    title = "Combining Linguistic Features for the Detection of {C}roatian Multiword Expressions",
    author = "Buljan, Maja  and
      {\v{S}}najder, Jan",
    editor = "Markantonatou, Stella  and
      Ramisch, Carlos  and
      Savary, Agata  and
      Vincze, Veronika",
    booktitle = "Proceedings of the 13th Workshop on Multiword Expressions ({MWE} 2017)",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W17-1727/",
    doi = "10.18653/v1/W17-1727",
    pages = "194--199",
    abstract = "As multiword expressions (MWEs) exhibit a range of idiosyncrasies, their automatic detection warrants the use of many different features. Tsvetkov and Wintner (2014) proposed a Bayesian network model that combines linguistically motivated features and also models their interactions. In this paper, we extend their model with new features and apply it to Croatian, a morphologically complex and a relatively free word order language, achieving a satisfactory performance of 0.823 F1-score. Furthermore, by comparing against (semi)naive Bayes models, we demonstrate that manually modeling feature interactions is indeed important. We make our annotated dataset of Croatian MWEs freely available."
}