<?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>2026-04-14T09:50:25Z</responseDate><request verb="GetRecord" identifier="oai:clarin.vdu.lt:20.500.11821/61" metadataPrefix="oai_dc">https://clarin.vdu.lt/oai/request</request><GetRecord><record><header><identifier>oai:clarin.vdu.lt:20.500.11821/61</identifier><datestamp>2024-12-20T07:12:32Z</datestamp><setSpec>hdl_20.500.11821_6</setSpec><setSpec>hdl_20.500.11821_7</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>Lithuanian morphologically annotated corpus - MATAS v3.0</dc:title>
<dc:creator>Rimkutė, Erika</dc:creator>
<dc:creator>Bielinskienė, Agnė</dc:creator>
<dc:creator>Dadurkevičius, Virginijus</dc:creator>
<dc:creator>Kovalevskaitė, Jolanta</dc:creator>
<dc:creator>Utka, Andrius</dc:creator>
<dc:creator>Boizou, Loïc</dc:creator>
<dc:subject>corpus</dc:subject>
<dc:subject>Lithuanian</dc:subject>
<dc:subject>annotated</dc:subject>
<dc:subject>morphology</dc:subject>
<dc:subject>CoNLL-U</dc:subject>
<dc:description>MATAS corpus (version 3.0)&#xd;
&#xd;
DESCRIPTION&#xd;
Updated, manually checked, morphologically annotated corpus MATAS&#xd;
&#xd;
LANGUAGE&#xd;
Lithuanian&#xd;
&#xd;
PREVIOUS VERSIONS&#xd;
1. MATAS v0.2 (http://hdl.handle.net/20.500.11821/9)&#xd;
2. MATAS v1.0 (http://hdl.handle.net/20.500.11821/33)&#xd;
&#xd;
FORMATS, STANDARTS&#xd;
1. CoNLL-U (https://universaldependencies.org/format.html);&#xd;
2. JABLONSKIS tagset v2 (https://sitti.vdu.lt/jablonskis-en/);&#xd;
3. MULTEXT-East tagset (http://nl.ijs.si/ME/V4/msd/html/index.html)&#xd;
4. UTF-8&#xd;
&#xd;
SIZE&#xd;
Tokens (incl. punctuation): 2,137,287&#xd;
Words: 1,694,819&#xd;
Sentences: 144,047&#xd;
Documents: 1,234&#xd;
&#xd;
GENRES&#xd;
Contains 5 genres: Documents (14%), Fiction (19%), Periodicals (36%), Scientific texts (24%), Transcripts(7%)&#xd;
&#xd;
PUBLISHER&#xd;
Institute of Digital Resources and Interdisciplinary Research (SITTI), Vytautas Magnus University</dc:description>
<dc:date>2024-12-19</dc:date>
<dc:type>corpus</dc:type>
<dc:identifier>http://hdl.handle.net/20.500.11821/61</dc:identifier>
<dc:language>lit</dc:language>
<dc:rights>PUB_CLARIN-LT_End-User-Licence-Agreement_EN-LT</dc:rights>
<dc:rights>https://clarin.vdu.lt/licenses/eula/PUB_CLARIN-LT_End-User-Licence-Agreement_EN-LT.htm</dc:rights>
<dc:rights>PUB</dc:rights>
<dc:format>text/plain; charset=utf-8</dc:format>
<dc:format>application/zip</dc:format>
<dc:format>text/plain</dc:format>
<dc:format>text/plain</dc:format>
<dc:format>downloadable_files_count: 3</dc:format>
<dc:publisher>Institute of Digital Resources and Interdisciplinary Research (SITTI), Vytautas Magnus University</dc:publisher>
</oai_dc:dc>
</metadata></record></GetRecord></OAI-PMH>