{"value":"\n<cmd:CMD xmlns:cmd=\"http://www.clarin.eu/cmd/\" xmlns:lindat=\"http://lindat.mff.cuni.cz/ns/experimental/cmdi\" xmlns:olac=\"http://www.clarin.eu/cmd/\" xmlns:ms=\"http://www.clarin.eu/cmd/\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" CMDVersion=\"1.1\" xsi:schemaLocation=\"http://www.clarin.eu/cmd/ http://catalog.clarin.eu/ds/ComponentRegistry/rest/registry/profiles/clarin.eu:cr1:p_1403526079380/xsd\">  \n  <cmd:Header> \n    <cmd:MdCreationDate>2023-04-14</cmd:MdCreationDate>  \n    <cmd:MdSelfLink>https://hdl.handle.net/11356/1206@format=cmdi</cmd:MdSelfLink>  \n    <cmd:MdProfile>clarin.eu:cr1:p_1403526079380</cmd:MdProfile>  \n    <cmd:MdCollectionDisplayName>CLARIN.SI data &amp; tools</cmd:MdCollectionDisplayName> \n  </cmd:Header>  \n  <cmd:Resources> \n    <cmd:ResourceProxyList> \n      <cmd:ResourceProxy id=\"lp_1744\"> \n        <cmd:ResourceType>LandingPage</cmd:ResourceType>  \n        <cmd:ResourceRef>https://hdl.handle.net/11356/1206</cmd:ResourceRef> \n      </cmd:ResourceProxy>  \n      <cmd:ResourceProxy id=\"_2694\"> \n        <cmd:ResourceType mimetype=\"application/octet-stream\">Resource</cmd:ResourceType>  \n        <cmd:ResourceRef lindat:md5_checksum=\"00cb8eb2c8a438178018bcff5b426f75\">https://www.clarin.si/repository/xmlui/bitstream/handle/11356/1206/embed.sr-lemma.ft.sg.bin?sequence=1</cmd:ResourceRef> \n      </cmd:ResourceProxy>  \n      <cmd:ResourceProxy id=\"_2695\"> \n        <cmd:ResourceType mimetype=\"application/gzip\">Resource</cmd:ResourceType>  \n        <cmd:ResourceRef lindat:md5_checksum=\"e8e69b35175e47bce8e8e7c7869a77cc\">https://www.clarin.si/repository/xmlui/bitstream/handle/11356/1206/embed.sr-lemma.ft.sg.vec.gz?sequence=2</cmd:ResourceRef> \n      </cmd:ResourceProxy>  \n      <cmd:ResourceProxy id=\"_2696\"> \n        <cmd:ResourceType mimetype=\"application/octet-stream\">Resource</cmd:ResourceType>  \n        <cmd:ResourceRef lindat:md5_checksum=\"fbfb884ff7746c0187e185ecd3a4a7e1\">https://www.clarin.si/repository/xmlui/bitstream/handle/11356/1206/embed.sr-token.ft.sg.bin?sequence=3</cmd:ResourceRef> \n      </cmd:ResourceProxy>  \n      <cmd:ResourceProxy id=\"_2697\"> \n        <cmd:ResourceType mimetype=\"application/gzip\">Resource</cmd:ResourceType>  \n        <cmd:ResourceRef lindat:md5_checksum=\"21b828b6287daa181f6eeb572a99948f\">https://www.clarin.si/repository/xmlui/bitstream/handle/11356/1206/embed.hr-token.ft.sg.vec.gz?sequence=4</cmd:ResourceRef> \n      </cmd:ResourceProxy> \n    </cmd:ResourceProxyList>  \n    <cmd:JournalFileProxyList/>  \n    <cmd:ResourceRelationList/> \n  </cmd:Resources>  \n  <cmd:Components> \n    <cmd:LINDAT_CLARIN> \n      <cmd:bibliographicInfo> \n        <cmd:titles> \n          <cmd:title xml:lang=\"en\">Word embeddings CLARIN.SI-embed.sr 1.0</cmd:title> \n        </cmd:titles>  \n        <cmd:authors> \n          <author xmlns=\"http://www.clarin.eu/cmd/\">  \n            <lastName>Ljubešić</lastName>  \n            <firstName>Nikola</firstName> \n          </author> \n        </cmd:authors>  \n        <cmd:dates> \n          <cmd:dateIssued>2018-12-10</cmd:dateIssued> \n        </cmd:dates>  \n        <cmd:identifiers> \n          <cmd:identifier type=\"Handle\">https://hdl.handle.net/11356/1206</cmd:identifier> \n        </cmd:identifiers>  \n        <cmd:funds> \n          <funding xmlns=\"http://www.clarin.eu/cmd/\">  \n            <organization>Jožef Stefan Institute</organization>  \n            <code>CLARIN</code>  \n            <projectName>CLARIN.SI</projectName>  \n            <fundsType>nationalFunds</fundsType> \n          </funding> \n        </cmd:funds>  \n        <contactPerson xmlns=\"http://www.clarin.eu/cmd/\">  \n          <firstName>Nikola</firstName>  \n          <lastName>Ljubešić</lastName>  \n          <email>nikola.ljubesic@ijs.si</email>  \n          <affiliation>Jožef Stefan Institute</affiliation> \n        </contactPerson>  \n        <cmd:publishers> \n          <cmd:publisher>Jožef Stefan Institute</cmd:publisher> \n        </cmd:publishers> \n      </cmd:bibliographicInfo>  \n      <cmd:dataInfo> \n        <cmd:type>lexicalConceptualResource</cmd:type>  \n        <cmd:detailedType>computationalLexicon</cmd:detailedType>  \n        <cmd:description>CLARIN.SI-embed.sr contains word embeddings induced from the srWaC web corpus. The embeddings are based on the skip-gram model of fastText trained on 554,606,544 tokens of running text for (1) 881,150 lowercased surface forms (e.g., \"srbije\") and (2) 599,416 lowercased lemmas with added part-of-speech information (e.g., \"srbija#Np\").</cmd:description>  \n        <cmd:languages> \n          <cmd:language> \n            <cmd:code>srp</cmd:code>  \n            <cmd:name>Serbian</cmd:name> \n          </cmd:language> \n        </cmd:languages>  \n        <cmd:keywords> \n          <cmd:keyword>word embeddings</cmd:keyword>  \n          <cmd:keyword>lemmatisation</cmd:keyword>  \n          <cmd:keyword>part-of-speech tagging</cmd:keyword> \n        </cmd:keywords>  \n        <cmd:sizeInfo> \n          <size xmlns=\"http://www.clarin.eu/cmd/\">  \n            <size>1480566</size>  \n            <unit>entries</unit> \n          </size> \n        </cmd:sizeInfo> \n      </cmd:dataInfo>  \n      <cmd:licenseInfo> \n        <cmd:license> \n          <cmd:uri>https://creativecommons.org/licenses/by/4.0/</cmd:uri> \n        </cmd:license> \n      </cmd:licenseInfo> \n    </cmd:LINDAT_CLARIN> \n  </cmd:Components> \n</cmd:CMD>"}