@inproceedings{muischnek-muurisep-2023-named,
    title = "Named Entity layer in {E}stonian {UD} treebanks",
    author = {Muischnek, Kadri  and
      M{\"u}{\"u}risep, Kaili},
    editor = {Alum{\"a}e, Tanel  and
      Fishel, Mark},
    booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
    month = may,
    year = "2023",
    address = "T{\'o}rshavn, Faroe Islands",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.nodalida-1.19/",
    pages = "179--184",
    abstract = "In this paper we will introduce two new language resources, two NE-annotated corpora for Estonian: Estonian Universal Dependencies Treebank (EDT, 440,000 tokens) and Estonian Universal Dependencies Web Treebank (EWT, 90,000 tokens). Together they make up the largest publicly available Estonian named entity gold annotation dataset. Eight NE categories are manually annotated in this dataset, and the fact that it is also annotated for lemma, POS, morphological features and dependency syntactic relations, makes it more valuable. We will also show that dividing the set of named entities into clear-cut categories is not always easy."
}