{"status":"OK","data":{"id":191044,"identifier":"ZUWAPS","persistentUrl":"https://doi.org/10.34894/ZUWAPS","protocol":"doi","authority":"10.34894","separator":"/","publisher":"DataverseNL","publicationDate":"2021-11-29","storageIdentifier":"surf://10.34894/ZUWAPS","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9996,"datasetType":"dataset","locks":[],"latestVersion":{"id":8810,"datasetId":191044,"datasetPersistentId":"doi:10.34894/ZUWAPS","datasetType":"dataset","storageIdentifier":"surf://10.34894/ZUWAPS","versionNumber":1,"internalVersionNumber":13,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionLink":"","lastUpdateTime":"2021-11-29T22:18:47Z","releaseTime":"2021-11-29T22:18:47Z","createTime":"2021-09-29T08:10:36Z","publicationDate":"2021-11-29","citationDate":"2021-11-29","effectiveDatasetFileCountLimit":10000,"datasetFileUploadsAvailable":9996,"license":{"name":"CC0-1.0","uri":"http://creativecommons.org/publicdomain/zero/1.0","iconUri":"https://licensebuttons.net/p/zero/1.0/88x31.png","rightsIdentifier":"CC0-1.0","rightsIdentifierScheme":"SPDX","schemeUri":"https://spdx.org/licenses/","languageCode":"en"},"fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"EXCEPTIUS Corpus"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Caselli, Tommaso"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Groningen"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0000-0003-2936-0256"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Egger, Clara"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Groningen"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Tziafas, Georgios"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Groningen"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"De Saint-Phalle, Eugenie"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Groningen"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Caselli, Tommaso"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"University of Groningen"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"EXCEPTIUS Corpus v1.0, containing the following data:<br>\n- raw documents for 21 countries at national level<br>\n- pre-processed data with spacy-udpipe v1.0<br>\n- automatically annotated documents for the identification of exceptional measures at sentence level<br>\n\n<br>\nCountry list (ISO 3166-1 alpha-2): AT, BE, HR, CY, CZ, DK, FR, DE, HU, IE, IT, LV, LT, NL, NO, PL, SI, SE, CH, UK \n<br>\n<br>\nFolder structure: each country has a dedicated folder. Inside each folder you will find the following subfolders: <br>\n- raw_text: the raw text data (.txt format) <br> \n- processed: the output of the spacy-udpipe v1.0 - each line is a sentence, containing the following info: tokens, lemma, POS, UD dependency relations<br>\n- model: the predictions of the trained model (XML pre@36 as reported in Table 4 of the paper). Each line is a sentence, separate by 9 tab - each for a exceptional measure class. 1: signals presence of a class.\n<br>\n<br>\nThe Italy and Norway folder misses the predictions of the models."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2021-11-26"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Arts and Humanities","Law","Social Sciences"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"SARS-CoV-2"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Natural Language Processing"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Multilingual Text Processing"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Exceptional Legislation"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Tziafas, G., De Saint-Phalle, E., de Vries, W., Egger, C., & Caselli, T. (2021). A Multilingual Approach to Identify and Classify Exceptional Measures against COVID-19. In N. Aletras, I. Androutsopoulos, L. Barrett, C. Goanta, & D. Preotiuc-Pietro (Eds.), Proceedings of the Natural Legal Language Processing Workshop 2021 (pp. 46-62). Association for Computational Linguistics (ACL)."},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"isbn"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"978-1-954085-98-5"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://aclanthology.org/2021.nllp-1.5/"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["Croatian","Czech","Danish","Dutch","English","French","German","Greek (modern)","Hungarian","Italian","Latvian","Lithuanian","Norwegian Bokmål","Polish","Slovenian","Spanish, Castilian","Swedish"]},{"typeName":"grantNumber","multiple":true,"typeClass":"compound","value":[{"grantNumberAgency":{"typeName":"grantNumberAgency","multiple":false,"typeClass":"primitive","value":"ZonMw"},"grantNumberValue":{"typeName":"grantNumberValue","multiple":false,"typeClass":"primitive","value":"10430032010026"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Elsenga, Christina"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2021-09-29"},{"typeName":"timePeriodCovered","multiple":true,"typeClass":"compound","value":[{"timePeriodCoveredStart":{"typeName":"timePeriodCoveredStart","multiple":false,"typeClass":"primitive","value":"2020-02-01"},"timePeriodCoveredEnd":{"typeName":"timePeriodCoveredEnd","multiple":false,"typeClass":"primitive","value":"2020-06-30"}}]},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["legal texts"]}]},"dansDataVaultMetadata":{"displayName":"Data Vault Metadata","name":"dansDataVaultMetadata","fields":[{"typeName":"dansDataversePid","multiple":false,"typeClass":"primitive","value":"doi:10.34894/ZUWAPS"},{"typeName":"dansDataversePidVersion","multiple":false,"typeClass":"primitive","value":"1.0"},{"typeName":"dansBagId","multiple":false,"typeClass":"primitive","value":"urn:uuid:ed600124-50be-4b3d-9dd1-48722427beab"},{"typeName":"dansNbn","multiple":false,"typeClass":"primitive","value":"urn:nbn:nl:ui:13-000b59e6-014e-4299-bd68-8b8d9c87d94e"}]}},"files":[{"label":"Automated data collection.docx","restricted":false,"version":1,"datasetVersionId":8810,"dataFile":{"id":199821,"persistentId":"","filename":"Automated data collection.docx","contentType":"application/vnd.openxmlformats-officedocument.wordprocessingml.document","friendlyType":"MS Word","filesize":6820,"storageIdentifier":"surf://store:17d5cc48ecb-9074532c1214","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"87c19ad2e00abe96dcdd4d36dc9c0d6150f64681"},"tabularData":false,"creationDate":"2021-11-26","publicationDate":"2021-11-29","lastUpdateTime":"2021-11-29T22:18:47Z","fileAccessRequest":false}},{"label":"Collecting the documents for the corpus - Guidelines.docx","restricted":false,"version":1,"datasetVersionId":8810,"dataFile":{"id":199819,"persistentId":"","filename":"Collecting the documents for the corpus - Guidelines.docx","contentType":"application/vnd.openxmlformats-officedocument.wordprocessingml.document","friendlyType":"MS Word","filesize":7681,"storageIdentifier":"surf://store:17d5cc44847-76d0bb2cf8a8","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"67807cf590bd112635620e9976ad8fa57b34ef2c"},"tabularData":false,"creationDate":"2021-11-26","publicationDate":"2021-11-29","lastUpdateTime":"2021-11-29T22:18:47Z","fileAccessRequest":false}},{"description":"Full corpus data for all the countries","label":"EXCEPTIUS_v1.zip","restricted":false,"version":1,"datasetVersionId":8810,"dataFile":{"id":199822,"persistentId":"","filename":"EXCEPTIUS_v1.zip","contentType":"application/zip","friendlyType":"ZIP Archive","filesize":233842395,"description":"Full corpus data for all the countries","storageIdentifier":"surf://store:17d5ccc012c-bbf59f14a54c","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"f7d794428b65f012b075662ab9e568c514ef9440"},"tabularData":false,"creationDate":"2021-11-26","publicationDate":"2021-11-29","lastUpdateTime":"2021-11-29T22:18:47Z","fileAccessRequest":false}},{"label":"Keywords ACA.xlsx","restricted":false,"version":1,"datasetVersionId":8810,"dataFile":{"id":199820,"persistentId":"","filename":"Keywords ACA.xlsx","contentType":"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet","friendlyType":"MS Excel Spreadsheet","filesize":9233,"storageIdentifier":"surf://store:17d5cc448d1-da47452b1300","rootDataFileId":-1,"checksum":{"type":"SHA-1","value":"02fcc4b9e49e67560e988fa9654122f9ee14a6ad"},"tabularData":false,"creationDate":"2021-11-26","publicationDate":"2021-11-29","lastUpdateTime":"2021-11-29T22:18:47Z","fileAccessRequest":false}}]}}}