{"dcterms:modified":"2025-11-24","dcterms:creator":"ARP","@type":"ore:ResourceMap","schema:additionalType":"Dataverse OREMap Format v1.0.0","dvcore:generatedBy":{"@type":"schema:SoftwareApplication","schema:name":"Dataverse","schema:version":"6.1 build arp-prod-e547759995","schema:url":"https://github.com/iqss/dataverse"},"@id":"https://repo.researchdata.hu/api/datasets/export?exporter=OAI_ORE&persistentId=https://hdl.handle.net/21.15109/CONCORDA/XTVX3U","ore:describes":{"subject":"Arts and Humanities","depositor":"Kalivoda, Ágnes","title":"PrevDistro","otherReferences":"If you use PrevDistro, please cite the following publication: Kalivoda, Ágnes (2021). Igekötős szerkezetek a magyarban [Preverb constructions in Hungarian]. PhD thesis. Pázmány Péter Catholic University, Budapest, Hungary. (to appear)","kindOfData":"corpus data","subtitle":"Preverb Distributions","language":"Hungarian","dateOfDeposit":"2021-06-21","dataSources":["PrevLex: https://github.com/kagnes/prevlex","Hungarian Gigaword Corpus (also known as HGC, MNSZ2): http://clara.nytud.hu/mnsz2-dev/"],"author":{"authorName":"Kalivoda, Ágnes","authorAffiliation":"Nyelvtudományi Kutatóközpont","authorIdentifierScheme":"ORCID","authorIdentifier":"0000-0003-2520-5523"},"publication":{"publicationCitation":"Kalivoda, Ágnes (2021). Igekötős szerkezetek a magyarban [Preverb constructions in Hungarian]. PhD thesis. Pázmány Péter Catholic University, Budapest, Hungary. (to appear) (https://github.com/kagnes/phd_thesis)"},"datasetContact":{"datasetContactName":"Kalivoda, Ágnes","datasetContactAffiliation":"Nyelvtudományi Kutatóközpont","datasetContactEmail":"kalivoda.agnes@nytud.hu"},"otherId":{"otherIdAgency":"DOI","otherIdValue":"10.5158/ARP/XTVX3U"},"keyword":[{"keywordValue":"linguistics"},{"keywordValue":"Hungarian language"},{"keywordValue":"preverb constructions"}],"dsDescription":[{"dsDescriptionValue":"PrevDistro (Preverb Distributions) is an open-source dataset containing 41.5 million corpus occurrences of 49 preverb-verb construction types. It consists of 10 columns which are as follows:"},{"dsDescriptionValue":"1st: ID"},{"dsDescriptionValue":"2nd: construction type"},{"dsDescriptionValue":"3rd: construction subtype"},{"dsDescriptionValue":"4th: preverb position"},{"dsDescriptionValue":"5th: preverb"},{"dsDescriptionValue":"6th: verb lemma"},{"dsDescriptionValue":"7th: intervening words (as lemmas)"},{"dsDescriptionValue":"8th: actual form"},{"dsDescriptionValue":"9th: document ID"},{"dsDescriptionValue":"10th: actual sentence from the Hungarian Gigaword Corpus, the actual form (KWIC) stands between < ... >"}],"@id":"https://hdl.handle.net/21.15109/CONCORDA/XTVX3U","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"2.1","schema:name":"PrevDistro","schema:dateModified":"2025-11-24 19:16:50.8","schema:datePublished":"2021-06-21","schema:creativeWorkStatus":"RELEASED","dvcore:termsOfUse":"This dataset is made available under a Creative Commons CC0 license with the following additional/modified terms and conditions: ","dvcore:citationRequirements":"If you use PrevDistro, please cite the following publication: Kalivoda, Ágnes (2021). Igekötős szerkezetek a magyarban [Preverb constructions in Hungarian]. PhD thesis. Pázmány Péter Catholic University, Budapest, Hungary. (to appear) ","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":false},"schema:includedInDataCatalog":"ARP","schema:isPartOf":{"schema:name":"Lexical Knowledge Representation Research Group / Lexikai tudásreprezentáció kutatócsoport","@id":"https://repo.researchdata.hu/dataverse/ltk","schema:description":"The medium-term goal of the Lexical Knowledge Representation research group is to create an online monolingual general purpose dictionary that meets 21st-century expectations and lexicographical standards, primarily using automated methods. The dictionary will be based on a large, one-billion-word representative corpus compiled from Hungarian texts produced between 2001 and 2020. Compared to paper-based dictionaries, this new methodological and advanced technology allows us to achieve quick results.\n<br><br>\nA Lexikai tudásreprezentáció kutatócsoport középtávú célja a 21. századi elvárásoknak és lexikográfiai szempontoknak megfelelő, döntő részben gépi automatikus módszerekkel egy olyan online értelmező szótár készítése, amely által bekapcsolódhatunk a nemzetközi lexikológiai kutatásokba is. A szótár alapját egy nagyméretű, egymilliárd szavas reprezentatív korpusz képezi, amelyet 2001 és 2020 közötti időszakban keletkezett magyar nyelvű szövegekből állítunk össze. A papíralapú szótárakhoz képest ezzel az új szakmódszertani és korszerű technológiával gyors eredményt érünk el.","schema:isPartOf":{"schema:name":"Institute for Lexicology / Lexikológiai Intézet","@id":"https://repo.researchdata.hu/dataverse/lexi","schema:description":"This is the dataverse of the Institute of Lexicology in the HUN-REN Hungarian Research Centre for Linguistics. The Institute for Lexicology's main project at present is to compile the Comprehensive Dictionary of Hungarian and maintenance of the database of the New Hungarian Etymological Dictionary; compiling a new version of a monolingual explanatory dictionary partly based on the Explanatory Dictionary of the Hungarian Language by corpus-driven methods; research in the field of lexicography.","schema:isPartOf":{"schema:name":"Hungarian Research Centre for Linguistics / Nyelvtudományi Kutatóközpont","@id":"https://repo.researchdata.hu/dataverse/nytud","schema:description":"Dataverse for the Hungarian Research Centre for Linguistics","schema:isPartOf":{"schema:name":"Hungarian Research Network","@id":"https://repo.researchdata.hu/dataverse/hun-ren","schema:description":"<h2>A HUN-REN Magyar Kutatási Hálózat intézményi tárolója</h2>\nA HUN-REN Magyar Kutatási Hálózat a magyar tudományos élet alappillérét jelentő kutatási hálózat. A hálózat tizenegy kutatóközpontjának, hét kutatóintézetének, továbbá egyetemeken és más közintézményekben működő 116 támogatott kutatócsoportjának kutatói a matematikai és természettudományok, az élettudományok, illetve a bölcsészet- és társadalomtudományok legváltozatosabb területein végeznek alap- és alkalmazott kutatásokat.","schema:isPartOf":{"schema:name":"ARP","@id":"https://repo.researchdata.hu/dataverse/root","schema:description":"This is the root dataverse collection for HUN-REN ARP."}}}}},"schema:inLanguage":"en","ore:aggregates":[{"schema:name":"PrevDistro.tsv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":80885,"@id":"hdl:21.15109/CONCORDA/XTVX3U/G0E9VU","schema:sameAs":"https://repo.researchdata.hu/api/access/datafile/:persistentId?persistentId=hdl:21.15109/CONCORDA/XTVX3U/G0E9VU","@type":"ore:AggregatedResource","schema:fileFormat":"text/tsv","dvcore:filesize":11463972539,"dvcore:storageIdentifier":"s3-sztaki://concorda:17a2eb4e774-85908202e664","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"e38075881a160342f62f0f36d4962002"}}],"schema:hasPart":["hdl:21.15109/CONCORDA/XTVX3U/G0E9VU"]},"@context":{"author":"http://purl.org/dc/terms/creator","authorAffiliation":"https://dataverse.org/schema/citation/authorAffiliation","authorIdentifier":"http://purl.org/spar/datacite/AgentIdentifier","authorIdentifierScheme":"http://purl.org/spar/datacite/AgentIdentifierScheme","authorName":"https://dataverse.org/schema/citation/authorName","dataSources":"https://www.w3.org/TR/prov-o/#wasDerivedFrom","datasetContact":"https://dataverse.org/schema/citation/datasetContact","datasetContactAffiliation":"https://dataverse.org/schema/citation/datasetContactAffiliation","datasetContactEmail":"https://dataverse.org/schema/citation/datasetContactEmail","datasetContactName":"https://dataverse.org/schema/citation/datasetContactName","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","depositor":"https://dataverse.org/schema/citation/depositor","dsDescription":"https://dataverse.org/schema/citation/dsDescription","dsDescriptionValue":"https://dataverse.org/schema/citation/dsDescriptionValue","dvcore":"https://dataverse.org/schema/core#","keyword":"https://dataverse.org/schema/citation/keyword","keywordValue":"https://dataverse.org/schema/citation/keywordValue","kindOfData":"http://rdf-vocabulary.ddialliance.org/discovery#kindOfData","language":"http://purl.org/dc/terms/language","ore":"http://www.openarchives.org/ore/terms/","otherId":"https://dataverse.org/schema/citation/otherId","otherIdAgency":"https://dataverse.org/schema/citation/otherIdAgency","otherIdValue":"https://dataverse.org/schema/citation/otherIdValue","otherReferences":"http://purl.org/dc/terms/references","publication":"http://purl.org/dc/terms/isReferencedBy","publicationCitation":"http://purl.org/dc/terms/bibliographicCitation","schema":"http://schema.org/","subject":"http://purl.org/dc/terms/subject","subtitle":"https://dataverse.org/schema/citation/subtitle","title":"http://purl.org/dc/terms/title"}}