{"@context":{"@language":"en","@vocab":"https://schema.org/","citeAs":"cr:citeAs","column":"cr:column","conformsTo":"dct:conformsTo","cr":"http://mlcommons.org/croissant/","rai":"http://mlcommons.org/croissant/RAI/","data":{"@id":"cr:data","@type":"@json"},"dataType":{"@id":"cr:dataType","@type":"@vocab"},"dct":"http://purl.org/dc/terms/","ddi-stats":"http://rdf-vocabulary.ddialliance.org/cv/SummaryStatisticType/2.1.2/","examples":{"@id":"cr:examples","@type":"@json"},"extract":"cr:extract","field":"cr:field","fileProperty":"cr:fileProperty","fileObject":"cr:fileObject","fileSet":"cr:fileSet","format":"cr:format","includes":"cr:includes","isLiveDataset":"cr:isLiveDataset","jsonPath":"cr:jsonPath","key":"cr:key","md5":"cr:md5","parentField":"cr:parentField","path":"cr:path","recordSet":"cr:recordSet","references":"cr:references","regex":"cr:regex","repeated":"cr:repeated","replace":"cr:replace","samplingRate":"cr:samplingRate","sc":"https://schema.org/","separator":"cr:separator","source":"cr:source","subField":"cr:subField","transform":"cr:transform"},"@type":"sc:Dataset","conformsTo":"http://mlcommons.org/croissant/1.1","name":"Czech word and MWE lists","url":"https://doi.org/10.18710/PGDWXC","creator":[{"@type":"Person","givenName":"Václav","familyName":"Cvrček","affiliation":{"@type":"Organization","name":"Czech National Corpus"},"sameAs":"https://orcid.org/0000-0003-3977-2393","@id":"https://orcid.org/0000-0003-3977-2393","identifier":"https://orcid.org/0000-0003-3977-2393","name":"Cvrček, Václav"}],"description":"This post contains word and MWE (multi-word expression) lists used for the operationalization of some of the linguistic features in the multi-dimensional analysis (MDA) of Czech project carried out at the Czech National Corpus. The MDA procedure requires identifying and operationalizing linguistic features relevant for register variation in the language under scrutiny. In the Czech MDA project, some of these features were operationalized by compiling lists of words and multi-word expressions, which can then be matched against a text to identify occurrences. Compiling such a list can be tedious and error prone work, which is why we provide ours as a resource for other linguists either to adopt wholesale or at least use as a starting point to build on top of.","keywords":["Arts and Humanities","multi-dimensional analysis","lexicon","Czech","word list"],"license":"http://creativecommons.org/publicdomain/zero/1.0","datePublished":"2020-04-09","dateModified":"2023-09-28","includedInDataCatalog":{"@type":"DataCatalog","name":"DataverseNO","url":"https://dataverse.no"},"publisher":{"@type":"Organization","name":"DataverseNO"},"version":"1.1","citeAs":"@data{PGDWXC_2020,author = {Cvrček, Václav},publisher = {DataverseNO},title = {Czech word and MWE lists},year = {2020},url = {https://doi.org/10.18710/PGDWXC}}","funder":[{"@type":"Organization","name":"European Regional Development Fund"}],"spatialCoverage":["Czech Republic"],"citation":[{"@type":"CreativeWork","name":"Cvrček, V., Komrsková, Z., Lukeš, D. et al. Comparing web-crawled and traditional corpora. Lang Resources & Evaluation (2020).","@id":"https://doi.org/10.1007/s10579-020-09487-4","identifier":"https://doi.org/10.1007/s10579-020-09487-4","url":"https://doi.org/10.1007/s10579-020-09487-4"},{"@type":"CreativeWork","name":"Cvrček, V., Komrsková, Z., Lukeš, D., Poukarová, P., Řehořková, A., & Zasina, A. (2018). From extra- to intratextual characteristics: Charting the space of variation in Czech through MDA, Corpus Linguistics and Linguistic Theory (published online ahead of print).","@id":"https://doi.org/10.1515/cllt-2018-0020","identifier":"https://doi.org/10.1515/cllt-2018-0020","url":"https://doi.org/10.1515/cllt-2018-0020"}],"temporalCoverage":["1990/2014"],"distribution":[{"@type":"cr:FileObject","@id":"00_README.docx","name":"00_README.docx","encodingFormat":"application/vnd.openxmlformats-officedocument.wordprocessingml.document","md5":"55e39b59b55c8e946a3de1e6b03b24ee","contentSize":"34412","description":"Start here.","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/LQYPHP"},{"@type":"cr:FileObject","@id":"00_README.pdf","name":"00_README.pdf","encodingFormat":"application/pdf","md5":"09437a34a9c9e3c9f2395e66de1e312a","contentSize":"415505","description":"Start here.","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/NHZH8K"},{"@type":"cr:FileObject","@id":"ASIM.txt","name":"ASIM.txt","encodingFormat":"text/plain","md5":"6e191dae1ef8328d3cbc6dd00093f21a","contentSize":"6453","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/HBSYAA"},{"@type":"cr:FileObject","@id":"AUG.txt","name":"AUG.txt","encodingFormat":"text/plain","md5":"eb748723bc3981669f75b3255da478f4","contentSize":"661","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/AQYZYI"},{"@type":"cr:FileObject","@id":"COH2.txt","name":"COH2.txt","encodingFormat":"text/plain","md5":"939ade9eaf84f7d71ace6bf9ed68cdd3","contentSize":"376","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/4OBJEG"},{"@type":"cr:FileObject","@id":"DEMI.txt","name":"DEMI.txt","encodingFormat":"text/plain","md5":"f0bb50319899cf22429886d200c723f1","contentSize":"9758","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/SOGZA7"},{"@type":"cr:FileObject","@id":"DP.txt","name":"DP.txt","encodingFormat":"text/plain","md5":"8fd609843cc9d84f7e5da44faa50c425","contentSize":"1441","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/CPWC3D"},{"@type":"cr:FileObject","@id":"DT.txt","name":"DT.txt","encodingFormat":"text/plain","md5":"1779529c7c6f212fd08d474e9d56c86b","contentSize":"1268","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/OM7Z7G"},{"@type":"cr:FileObject","@id":"EXP.txt","name":"EXP.txt","encodingFormat":"text/plain","md5":"a73195a2ec0294a5119530d4e1b509ba","contentSize":"1591","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/0IKRV6"},{"@type":"cr:FileObject","@id":"FEI.txt","name":"FEI.txt","encodingFormat":"text/plain","md5":"250f2b2bbec4744c231c4582c3354c2c","contentSize":"3611","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/HBH8IP"},{"@type":"cr:FileObject","@id":"FOUU.txt","name":"FOUU.txt","encodingFormat":"text/plain","md5":"2f71c0e5e3038990f249fc93360c0a34","contentSize":"4166","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/RJMBJK"},{"@type":"cr:FileObject","@id":"FUOU.txt","name":"FUOU.txt","encodingFormat":"text/plain","md5":"c1c92027b643c22d4f3ead9a4d6706a4","contentSize":"797","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/QRG5HO"},{"@type":"cr:FileObject","@id":"FYEJ.txt","name":"FYEJ.txt","encodingFormat":"text/plain","md5":"d27652fa1b186c879c185e8bc0d1c89b","contentSize":"13261","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/WEWH0J"},{"@type":"cr:FileObject","@id":"GENL.txt","name":"GENL.txt","encodingFormat":"text/plain","md5":"0813b1a76255f201e63e0eb462b63ae4","contentSize":"39474","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/UIOVCF"},{"@type":"cr:FileObject","@id":"GRAAA.txt","name":"GRAAA.txt","encodingFormat":"text/plain","md5":"7f9c29f6e1ecb26ec793f23dc8d3c695","contentSize":"20048","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/2L0WCX"},{"@type":"cr:FileObject","@id":"KONT.txt","name":"KONT.txt","encodingFormat":"text/plain","md5":"250e805f106ca7220c3b072894ba6066","contentSize":"678","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/ZP0VNT"},{"@type":"cr:FileObject","@id":"LAT.txt","name":"LAT.txt","encodingFormat":"text/plain","md5":"57740e65c972064fb255cd88b9200455","contentSize":"774","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/V3AFIK"},{"@type":"cr:FileObject","@id":"MOD.txt","name":"MOD.txt","encodingFormat":"text/plain","md5":"c1f371c112a335e9804621e32939df31","contentSize":"663","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/VQB3P5"},{"@type":"cr:FileObject","@id":"PAJ.txt","name":"PAJ.txt","encodingFormat":"text/plain","md5":"dae3f455731d1ff407353b5e14d95f0a","contentSize":"1261","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/OIBHQD"},{"@type":"cr:FileObject","@id":"PAV.txt","name":"PAV.txt","encodingFormat":"text/plain","md5":"79481fda1fd276cc9d21016e3189a898","contentSize":"389","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/0BHZIA"},{"@type":"cr:FileObject","@id":"POE.txt","name":"POE.txt","encodingFormat":"text/plain","md5":"b6cd1d685373114d99703a1a35d00bd2","contentSize":"10252","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/6LSQ66"},{"@type":"cr:FileObject","@id":"PRE2.txt","name":"PRE2.txt","encodingFormat":"text/plain","md5":"334f6ae90d53f31a59a7e0f797a2099c","contentSize":"6891","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/TVCY3D"},{"@type":"cr:FileObject","@id":"PROPA.txt","name":"PROPA.txt","encodingFormat":"text/plain","md5":"7bb8457f4903063ecb881f0ba0c4729f","contentSize":"8296","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/RCWQIB"},{"@type":"cr:FileObject","@id":"PROPT.txt","name":"PROPT.txt","encodingFormat":"text/plain","md5":"e297b5d99e667df8de0e416bc088596a","contentSize":"1595","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/LMBA5O"},{"@type":"cr:FileObject","@id":"PSB.txt","name":"PSB.txt","encodingFormat":"text/plain","md5":"f0937592e82909ac6c54cb12b63fc5c8","contentSize":"2002","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/6IZENY"},{"@type":"cr:FileObject","@id":"PVB.txt","name":"PVB.txt","encodingFormat":"text/plain","md5":"38f84fe3b757455f15df83e5cd626e00","contentSize":"2310","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/QFGZQY"},{"@type":"cr:FileObject","@id":"RST.txt","name":"RST.txt","encodingFormat":"text/plain","md5":"0f479c2d29215d9f26eaf40c4af0d778","contentSize":"314","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/EMPVKB"},{"@type":"cr:FileObject","@id":"VD.txt","name":"VD.txt","encodingFormat":"text/plain","md5":"161f4054724e43ec927f920197ffd692","contentSize":"1058","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/U7CUYJ"},{"@type":"cr:FileObject","@id":"VTS.txt","name":"VTS.txt","encodingFormat":"text/plain","md5":"74c68ad2b6e44ec01d15c40645cbd2e7","contentSize":"613","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/KRPYZS"},{"@type":"cr:FileObject","@id":"VUL.txt","name":"VUL.txt","encodingFormat":"text/plain","md5":"ad9267649cd5bd07c53fe092ed7ad0da","contentSize":"18675","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/6GFUUT"},{"@type":"cr:FileObject","@id":"VYPW.txt","name":"VYPW.txt","encodingFormat":"text/plain","md5":"58396033b2269f80110f57f6beb88501","contentSize":"203","description":"","contentUrl":"https://dataverse.no/api/access/datafile/:persistentId?persistentId=doi:10.18710/PGDWXC/VLMXD3"}]}