{"data":{"id":"10.6084/m9.figshare.3382774.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.3382774.v1","prefix":"10.6084","suffix":"m9.figshare.3382774.v1","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Baumann, Ryan","nameType":"Personal","givenName":"Ryan","familyName":"Baumann","affiliation":[],"nameIdentifiers":[{"schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-9249-1617","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"HTRC Extracted Features [v.0.2] `langid`"}],"publisher":"figshare","container":{},"publicationYear":2016,"subjects":[{"subject":"Digital Humanities"},{"subject":"Linguistics"},{"subject":"FOS: Languages and literature","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Languages and literature","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"Literature"},{"subject":"Language"},{"subject":"80107 Natural Language Processing","subjectScheme":"FOR"},{"subject":"FOS: Computer and information sciences","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Computer and information sciences","subjectScheme":"Fields of Science and Technology (FOS)"}],"contributors":[],"dates":[{"date":"2016-05-16","dateType":"Created"},{"date":"2016-05-16","dateType":"Updated"},{"date":"2016","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.3382774","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["655453109 Bytes"],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This archive contains the results of computing `langid` for the OCR tokens of each page in every volume of the HathiTrust HTRC Extracted Features [v.0.2] dataset. Each file is a CSV file of ISO639-1 language code and probability pairs for each page, where the filename is `[HTRC-volume-identifier].basic.json.csv`. Version 1.1.5 of `langid` was used for processing.\u003cbr\u003e\u003cb\u003eWarning:\u003c/b\u003e this archive will decompress to a ~25GB directory containing 4,805,434 files.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://figshare.com/articles/dataset/HTRC_Extracted_Features_v_0_2_langid_/3382774/1","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":1,"viewsOverTime":[{"yearMonth":"2026-05","total":1}],"downloadCount":0,"downloadsOverTime":[{"yearMonth":"2026-05","total":0}],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2016-05-16T20:47:02.000Z","registered":"2016-05-16T20:47:03.000Z","published":"2016","updated":"2020-09-04T10:57:32.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.3382774.v1","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}