<?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>2026-05-21T19:14:11Z</responseDate><request verb="GetRecord" identifier="oai:www.clarin.si:11356/1681" metadataPrefix="oai_dc">http://www.clarin.si/repository/oai/request</request><GetRecord><record><header><identifier>oai:www.clarin.si:11356/1681</identifier><datestamp>2023-10-23T17:56:52Z</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>Monitor corpus of Slovene Trendi 2022-10</dc:title>
<dc:creator>Kosem, Iztok</dc:creator>
<dc:creator>Čibej, Jaka</dc:creator>
<dc:creator>Dobrovoljc, Kaja</dc:creator>
<dc:creator>Erjavec, Tomaž</dc:creator>
<dc:creator>Ljubešić, Nikola</dc:creator>
<dc:creator>Ponikvar, Primož</dc:creator>
<dc:creator>Šinkec, Mihael</dc:creator>
<dc:creator>Krek, Simon</dc:creator>
<dc:subject>monitor corpus</dc:subject>
<dc:subject>news corpus</dc:subject>
<dc:subject>universal dependencies</dc:subject>
<dc:subject>temporal trends</dc:subject>
<dc:subject>topic attribution</dc:subject>
<dc:description>The Trendi corpus is a monitor corpus of Slovene. It contains news from 106 different media websites, published by 48 different publishers. Trendi 2022-10 covers the period from January 2019 to October 2022, complementing the Gigafida 2.0 reference corpus of written Slovene (http://hdl.handle.net/11356/1320). All the contents of the Trendi corpus are at the moment obtained using the Jožef Stefan Institute Newsfeed service (http://newsfeed.ijs.si/).&#xd;
&#xd;
The texts have been annotated using the CLASSLA-Stanza pipeline (https://github.com/clarinsi/classla), including syntactic parsing according to the Universal Dependencies (https://universaldependencies.org/sl/) and Named Entities (https://nl.ijs.si/janes/wp-content/uploads/2017/09/SlovenianNER-eng-v1.1.pdf).&#xd;
&#xd;
An important addition to this version are topics or thematical categories, which have been automatically assigned to each text. There are 13 categories altogether: Arts and culture, Crime and accidents, Economy, Environment, Health, Leisure, Politics and Law, Science and Technology, Society, Sports, Weather, Entertainment, and Education. Text classification models are available at http://hdl.handle.net/11356/1709 (Text classification model SloBERTa-Trendi-Topics 1.0), http://hdl.handle.net/11356/1710 (Text classification model fastText-Trendi-Topics 1.0), and https://huggingface.co/cjvt/sloberta-trendi-topics (SloBERTa model).&#xd;
&#xd;
At the moment, the corpus is not available as a dataset due to copyright restrictions but we hope to make at least some of it available in the near future. The corpus is accessible through CLARIN.SI concordancers.</dc:description>
<dc:date>2022-11-21</dc:date>
<dc:type>corpus</dc:type>
<dc:identifier>http://hdl.handle.net/11356/1681</dc:identifier>
<dc:language>slv</dc:language>
<dc:relation>http://euralex.org/wp-content/themes/euralex/proceedings/Euralex%202022/EURALEX2022_Pr_p230-239_Kosem.pdf</dc:relation>
<dc:relation>https://nl.ijs.si/jtdh22/pdf/JTDH2022_Kosem-et-al_Spremljevalni-korpus-Trendi.pdf</dc:relation>
<dc:relation>http://hdl.handle.net/11356/1590</dc:relation>
<dc:relation>http://hdl.handle.net/11356/1782</dc:relation>
<dc:format>downloadable_files_count: 0</dc:format>
<dc:publisher>Jožef Stefan Institute</dc:publisher>
<dc:source>https://sled.ijs.si/</dc:source>
</oai_dc:dc>
</metadata></record></GetRecord></OAI-PMH>