<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-06-22T00:38:03Z</responseDate><request verb="GetRecord" identifier="oai:www.clarin.si:11356/1275" metadataPrefix="oai_dc">http://www.clarin.si/repository/oai/request</request><GetRecord><record><header><identifier>oai:www.clarin.si:11356/1275</identifier><datestamp>2023-03-27T17:01:19Z</datestamp><setSpec>hdl_11356_1023</setSpec><setSpec>hdl_11356_1024</setSpec></header><metadata><oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title>Frequency lists of word parts from the Gigafida 2.0 corpus</dc:title>
<dc:creator>Čibej, Jaka</dc:creator>
<dc:creator>Arhar Holdt, Špela</dc:creator>
<dc:creator>Dobrovoljc, Kaja</dc:creator>
<dc:creator>Krek, Simon</dc:creator>
<dc:subject>word parts</dc:subject>
<dc:subject>morphology</dc:subject>
<dc:subject>standard language</dc:subject>
<dc:subject>frequency list</dc:subject>
<dc:subject>initial part of the word</dc:subject>
<dc:subject>final part of the word</dc:subject>
<dc:description>Frequency lists of words split into word parts were extracted from the Gigafida 2.0 Corpus of Written Standard Slovene (https://viri.cjvt.si/gigafida/) using the LIST corpus extraction tool (http://hdl.handle.net/11356/1227). The lists contain all lemmas or lower-case word forms occurring in the corpus, split into their initial or final part (i.e. the initial or final string of 1, 2, 3, 4 or 5 characters in the word) and the rest of the word. In addition, the lists also contain absolute and relative frequencies, percentages, and distribution across the text-types included in the corpus taxonomy.&#xd;
&#xd;
The lists were extracted for each part-of-speech category. For each part-of-speech, a total of 20 lists were extracted:&#xd;
1) 10 lists for initial or final word parts extracted from lemmas,&#xd;
2) 10 lists for initial or final word parts extracted from lower-case word forms.&#xd;
&#xd;
In addition, 20 lists were extracted from all words (regardless of their part-of-speech category). For easier processing in statistical analysis software, shortened versions of longer lists were made containing the first 150,000 lines.</dc:description>
<dc:date>2019-11-18</dc:date>
<dc:type>lexicalConceptualResource</dc:type>
<dc:identifier>http://hdl.handle.net/11356/1275</dc:identifier>
<dc:language>slv</dc:language>
<dc:rights>Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)</dc:rights>
<dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights>
<dc:rights>PUB</dc:rights>
<dc:format>text/plain; charset=utf-8</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>downloadable_files_count: 30</dc:format>
<dc:publisher>Centre for Language Resources and Technologies, University of Ljubljana</dc:publisher>
<dc:publisher>Jožef Stefan Institute</dc:publisher>
<dc:source>http://slovnica.ijs.si/</dc:source>
</oai_dc:dc>
</metadata></record></GetRecord></OAI-PMH>