{"id":246,"identifier":"CONCORDA/XTVX3U","persistentUrl":"https://hdl.handle.net/21.15109/CONCORDA/XTVX3U","protocol":"hdl","authority":"21.15109","publisher":"ARP","publicationDate":"2021-06-21","storageIdentifier":"s3-sztaki://21.15109/CONCORDA/XTVX3U","metadataLanguage":"en","datasetVersion":{"id":80885,"datasetId":246,"datasetPersistentId":"hdl:21.15109/CONCORDA/XTVX3U","storageIdentifier":"s3-sztaki://21.15109/CONCORDA/XTVX3U","versionNumber":2,"versionMinorNumber":1,"versionState":"RELEASED","lastUpdateTime":"2025-11-24T18:16:50Z","releaseTime":"2025-11-24T18:16:50Z","createTime":"2025-11-24T18:15:57Z","publicationDate":"2021-06-21","citationDate":"2021-06-21","termsOfUse":"This dataset is made available under a Creative Commons CC0 license with the following additional/modified terms and conditions: ","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) ","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"PrevDistro"},{"typeName":"subtitle","multiple":false,"typeClass":"primitive","value":"Preverb Distributions"},{"typeName":"otherId","multiple":true,"typeClass":"compound","value":[{"otherIdAgency":{"typeName":"otherIdAgency","multiple":false,"typeClass":"primitive","value":"DOI"},"otherIdValue":{"typeName":"otherIdValue","multiple":false,"typeClass":"primitive","value":"10.5158/ARP/XTVX3U"}}]},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Kalivoda, Ágnes"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Nyelvtudományi Kutatóközpont"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0003-2520-5523"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Kalivoda, Ágnes"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Nyelvtudományi Kutatóközpont"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"kalivoda.agnes@nytud.hu"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"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":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"1st: ID"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"2nd: construction type"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"3rd: construction subtype"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"4th: preverb position"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"5th: preverb"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"6th: verb lemma"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"7th: intervening words (as lemmas)"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"8th: actual form"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"9th: document ID"}},{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"10th: actual sentence from the Hungarian Gigaword Corpus, the actual form (KWIC) stands between < ... >"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Arts and Humanities"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"linguistics"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Hungarian language"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"preverb constructions"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"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)"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["Hungarian"]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Kalivoda, Ágnes"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2021-06-21"},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["corpus data"]},{"typeName":"otherReferences","multiple":true,"typeClass":"primitive","value":["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)"]},{"typeName":"dataSources","multiple":true,"typeClass":"primitive","value":["PrevLex: https://github.com/kagnes/prevlex","Hungarian Gigaword Corpus (also known as HGC, MNSZ2): http://clara.nytud.hu/mnsz2-dev/"]}]},"geospatial":{"displayName":"Geospatial Metadata","name":"geospatial","fields":[]},"journal":{"displayName":"Journal Metadata","name":"journal","fields":[]}},"files":[{"label":"PrevDistro.tsv","restricted":false,"version":1,"datasetVersionId":80885,"dataFile":{"id":247,"persistentId":"hdl:21.15109/CONCORDA/XTVX3U/G0E9VU","pidURL":"https://hdl.handle.net/21.15109/CONCORDA/XTVX3U/G0E9VU","filename":"PrevDistro.tsv","contentType":"text/tsv","friendlyType":"Tab-Separated Values","filesize":11463972539,"storageIdentifier":"s3-sztaki://concorda:17a2eb4e774-85908202e664","rootDataFileId":-1,"md5":"e38075881a160342f62f0f36d4962002","checksum":{"type":"MD5","value":"e38075881a160342f62f0f36d4962002"},"tabularData":false,"creationDate":"2021-06-21","publicationDate":"2021-06-21","fileAccessRequest":false}}],"citation":"Kalivoda, Ágnes, 2021, \"PrevDistro\", https://hdl.handle.net/21.15109/CONCORDA/XTVX3U, ARP, V2"}}