{"data":{"id":"10.6084/m9.figshare.5432128.v2","type":"dois","attributes":{"doi":"10.6084/m9.figshare.5432128.v2","prefix":"10.6084","suffix":"m9.figshare.5432128.v2","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Gómez, Candelario Hernández","nameType":"Personal","givenName":"Candelario Hernández","familyName":"Gómez","affiliation":[],"nameIdentifiers":[]},{"name":"Basurto-Flores, Rogelio","nameType":"Personal","givenName":"Rogelio","familyName":"Basurto-Flores","affiliation":[],"nameIdentifiers":[]},{"name":"Guzmanv, Lev","nameType":"Personal","givenName":"Lev","familyName":"Guzmanv","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"A corpus of 42 books from European languages embracing four families."}],"publisher":"figshare","container":{},"publicationYear":2017,"subjects":[{"subject":"80607 Information Engineering and Theory","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)"},{"subject":"200304 Central and Eastern European Languages (incl. Russian)","subjectScheme":"FOR"},{"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":"200322 Comparative Language Studies","subjectScheme":"FOR"},{"subject":"200524 Comparative Literature Studies","subjectScheme":"FOR"},{"subject":"200402 Computational Linguistics","subjectScheme":"FOR"},{"subject":"200306 French Language","subjectScheme":"FOR"},{"subject":"200307 German Language","subjectScheme":"FOR"},{"subject":"200302 English Language","subjectScheme":"FOR"},{"subject":"200309 Italian Language","subjectScheme":"FOR"},{"subject":"200510 Latin and Classical Greek Literature","subjectScheme":"FOR"},{"subject":"200408 Linguistic Structures (incl. Grammar, Phonology, Lexicon, Semantics)","subjectScheme":"FOR"},{"subject":"200511 Literature in French","subjectScheme":"FOR"},{"subject":"200512 Literature in German","subjectScheme":"FOR"},{"subject":"200513 Literature in Italian","subjectScheme":"FOR"},{"subject":"200514 Literature in Spanish and Portuguese","subjectScheme":"FOR"},{"subject":"200310 Other European Languages","subjectScheme":"FOR"},{"subject":"200515 Other European Literature","subjectScheme":"FOR"}],"contributors":[],"dates":[{"date":"2017-09-22","dateType":"Created"},{"date":"2017-09-22","dateType":"Updated"},{"date":"2017","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.5432128","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["38787 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":"A corpus of 42 books, three for each of 14 different European languages taken from the page www.gutenberg.org. The titles of the oeuvres and authors are written in the romanized way given in the page. The texts were chosen by no other reason that to be representative of each language and avoiding, as much as possible, the repetitive texts like poetry. \u003cbr\u003e","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iVVRGLTgiPz4KPHJlc291cmNlIHhtbG5zPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCIgeG1sbnM6eHNpPSJodHRwOi8vd3d3LnczLm9yZy8yMDAxL1hNTFNjaGVtYS1pbnN0YW5jZSIgeHNpOnNjaGVtYUxvY2F0aW9uPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCBodHRwOi8vc2NoZW1hLmRhdGFjaXRlLm9yZy9tZXRhL2tlcm5lbC00LjEvbWV0YWRhdGEueHNkIj4KICA8aWRlbnRpZmllciBpZGVudGlmaWVyVHlwZT0iRE9JIj4xMC42MDg0L005LkZJR1NIQVJFLjU0MzIxMjguVjI8L2lkZW50aWZpZXI+CiAgPGNyZWF0b3JzPgogICAgPGNyZWF0b3I+CiAgICAgIDxjcmVhdG9yTmFtZT5DYW5kZWxhcmlvIEhlcm7DoW5kZXogR8OzbWV6PC9jcmVhdG9yTmFtZT4KICAgIDwvY3JlYXRvcj4KICAgIDxjcmVhdG9yPgogICAgICA8Y3JlYXRvck5hbWU+Um9nZWxpbyBCYXN1cnRvLUZsb3JlczwvY3JlYXRvck5hbWU+CiAgICA8L2NyZWF0b3I+CiAgICA8Y3JlYXRvcj4KICAgICAgPGNyZWF0b3JOYW1lPkxldiBHdXptYW52PC9jcmVhdG9yTmFtZT4KICAgIDwvY3JlYXRvcj4KICA8L2NyZWF0b3JzPgogIDx0aXRsZXM+CiAgICA8dGl0bGU+QSBjb3JwdXMgb2YgNDIgYm9va3MgZnJvbSBFdXJvcGVhbiBsYW5ndWFnZXMgZW1icmFjaW5nIGZvdXIgZmFtaWxpZXMuPC90aXRsZT4KICA8L3RpdGxlcz4KICA8ZGVzY3JpcHRpb25zPgogICAgPGRlc2NyaXB0aW9uIGRlc2NyaXB0aW9uVHlwZT0iQWJzdHJhY3QiPkEgY29ycHVzIG9mIDQyIGJvb2tzLCB0aHJlZSBmb3IgZWFjaCBvZiAxNCBkaWZmZXJlbnQgRXVyb3BlYW4gbGFuZ3VhZ2VzIHRha2VuIGZyb20gdGhlIHBhZ2Ugd3d3Lmd1dGVuYmVyZy5vcmcuIFRoZSB0aXRsZXMgb2YgdGhlIG9ldXZyZXMgIGFuZCBhdXRob3JzIGFyZSB3cml0dGVuIGluIHRoZSByb21hbml6ZWQgd2F5IGdpdmVuIGluIHRoZSBwYWdlLiBUaGUgdGV4dHMgd2VyZSBjaG9zZW4gYnkgbm8gb3RoZXIgcmVhc29uIHRoYXQgdG8gYmUgcmVwcmVzZW50YXRpdmUgb2YgZWFjaCBsYW5ndWFnZSBhbmQgYXZvaWRpbmcsIGFzIG11Y2ggYXMgcG9zc2libGUsIHRoZSByZXBldGl0aXZlIHRleHRzIGxpa2UgcG9ldHJ5LiAgJmx0O2JyJmd0OzwvZGVzY3JpcHRpb24+CiAgPC9kZXNjcmlwdGlvbnM+CiAgPHN1YmplY3RzPgogICAgPHN1YmplY3Qgc2NoZW1lVVJJPSJodHRwOi8vd3d3LmFicy5nb3YuYXUvYXVzc3RhdHMvYWJzQC5uc2YvMC82QkI0MjdBQjk2OTZDMjI1Q0EyNTc0MTgwMDA0NDYzRSIgc3ViamVjdFNjaGVtZT0iRk9SIj44MDYwNyBJbmZvcm1hdGlvbiBFbmdpbmVlcmluZyBhbmQgVGhlb3J5PC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc2NoZW1lVVJJPSJodHRwOi8vd3d3LmFicy5nb3YuYXUvYXVzc3RhdHMvYWJzQC5uc2YvMC82QkI0MjdBQjk2OTZDMjI1Q0EyNTc0MTgwMDA0NDYzRSIgc3ViamVjdFNjaGVtZT0iRk9SIj4yMDAzMDQgQ2VudHJhbCBhbmQgRWFzdGVybiBFdXJvcGVhbiBMYW5ndWFnZXMgKGluY2wuIFJ1c3NpYW4pPC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc2NoZW1lVVJJPSJodHRwOi8vd3d3LmFicy5nb3YuYXUvYXVzc3RhdHMvYWJzQC5uc2YvMC82QkI0MjdBQjk2OTZDMjI1Q0EyNTc0MTgwMDA0NDYzRSIgc3ViamVjdFNjaGVtZT0iRk9SIj4yMDAzMjIgQ29tcGFyYXRpdmUgTGFuZ3VhZ2UgU3R1ZGllczwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwNTI0IENvbXBhcmF0aXZlIExpdGVyYXR1cmUgU3R1ZGllczwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwNDAyIENvbXB1dGF0aW9uYWwgTGluZ3Vpc3RpY3M8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzY2hlbWVVUkk9Imh0dHA6Ly93d3cuYWJzLmdvdi5hdS9hdXNzdGF0cy9hYnNALm5zZi8wLzZCQjQyN0FCOTY5NkMyMjVDQTI1NzQxODAwMDQ0NjNFIiBzdWJqZWN0U2NoZW1lPSJGT1IiPjIwMDMwNiBGcmVuY2ggTGFuZ3VhZ2U8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzY2hlbWVVUkk9Imh0dHA6Ly93d3cuYWJzLmdvdi5hdS9hdXNzdGF0cy9hYnNALm5zZi8wLzZCQjQyN0FCOTY5NkMyMjVDQTI1NzQxODAwMDQ0NjNFIiBzdWJqZWN0U2NoZW1lPSJGT1IiPjIwMDMwNyBHZXJtYW4gTGFuZ3VhZ2U8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzY2hlbWVVUkk9Imh0dHA6Ly93d3cuYWJzLmdvdi5hdS9hdXNzdGF0cy9hYnNALm5zZi8wLzZCQjQyN0FCOTY5NkMyMjVDQTI1NzQxODAwMDQ0NjNFIiBzdWJqZWN0U2NoZW1lPSJGT1IiPjIwMDMwMiBFbmdsaXNoIExhbmd1YWdlPC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc2NoZW1lVVJJPSJodHRwOi8vd3d3LmFicy5nb3YuYXUvYXVzc3RhdHMvYWJzQC5uc2YvMC82QkI0MjdBQjk2OTZDMjI1Q0EyNTc0MTgwMDA0NDYzRSIgc3ViamVjdFNjaGVtZT0iRk9SIj4yMDAzMDkgSXRhbGlhbiBMYW5ndWFnZTwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwNTEwIExhdGluIGFuZCBDbGFzc2ljYWwgR3JlZWsgTGl0ZXJhdHVyZTwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwNDA4IExpbmd1aXN0aWMgU3RydWN0dXJlcyAoaW5jbC4gR3JhbW1hciwgUGhvbm9sb2d5LCBMZXhpY29uLCBTZW1hbnRpY3MpPC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc2NoZW1lVVJJPSJodHRwOi8vd3d3LmFicy5nb3YuYXUvYXVzc3RhdHMvYWJzQC5uc2YvMC82QkI0MjdBQjk2OTZDMjI1Q0EyNTc0MTgwMDA0NDYzRSIgc3ViamVjdFNjaGVtZT0iRk9SIj4yMDA1MTEgTGl0ZXJhdHVyZSBpbiBGcmVuY2g8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzY2hlbWVVUkk9Imh0dHA6Ly93d3cuYWJzLmdvdi5hdS9hdXNzdGF0cy9hYnNALm5zZi8wLzZCQjQyN0FCOTY5NkMyMjVDQTI1NzQxODAwMDQ0NjNFIiBzdWJqZWN0U2NoZW1lPSJGT1IiPjIwMDUxMiBMaXRlcmF0dXJlIGluIEdlcm1hbjwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwNTEzIExpdGVyYXR1cmUgaW4gSXRhbGlhbjwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwNTE0IExpdGVyYXR1cmUgaW4gU3BhbmlzaCBhbmQgUG9ydHVndWVzZTwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwMzEwIE90aGVyIEV1cm9wZWFuIExhbmd1YWdlczwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+MjAwNTE1IE90aGVyIEV1cm9wZWFuIExpdGVyYXR1cmU8L3N1YmplY3Q+CiAgPC9zdWJqZWN0cz4KICA8cHVibGlzaGVyPmZpZ3NoYXJlPC9wdWJsaXNoZXI+CiAgPHB1YmxpY2F0aW9uWWVhcj4yMDE3PC9wdWJsaWNhdGlvblllYXI+CiAgPGRhdGVzPgogICAgPGRhdGUgZGF0ZVR5cGU9IkNyZWF0ZWQiPjIwMTctMDktMjI8L2RhdGU+CiAgICA8ZGF0ZSBkYXRlVHlwZT0iVXBkYXRlZCI+MjAxNy0wOS0yMjwvZGF0ZT4KICA8L2RhdGVzPgogIDxyZXNvdXJjZVR5cGUgcmVzb3VyY2VUeXBlR2VuZXJhbD0iRGF0YXNldCI+RGF0YXNldDwvcmVzb3VyY2VUeXBlPgogIDxzaXplcz4KICAgIDxzaXplPjM4Nzg3IEJ5dGVzPC9zaXplPgogIDwvc2l6ZXM+CiAgPHJlbGF0ZWRJZGVudGlmaWVycz4KICAgIDxyZWxhdGVkSWRlbnRpZmllciByZWxhdGVkSWRlbnRpZmllclR5cGU9IkRPSSIgcmVsYXRpb25UeXBlPSJJc0lkZW50aWNhbFRvIj4xMC42MDg0L205LmZpZ3NoYXJlLjU0MzIxMjg8L3JlbGF0ZWRJZGVudGlmaWVyPgogIDwvcmVsYXRlZElkZW50aWZpZXJzPgogIDxyaWdodHNMaXN0PgogICAgPHJpZ2h0cyByaWdodHNVUkk9Imh0dHBzOi8vY3JlYXRpdmVjb21tb25zLm9yZy9saWNlbnNlcy9ieS80LjAvIj5DQyBCWSA0LjA8L3JpZ2h0cz4KICA8L3JpZ2h0c0xpc3Q+CjwvcmVzb3VyY2U+","url":"https://figshare.com/articles/dataset/The_corpus/5432128/2","contentUrl":null,"metadataVersion":6,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":3,"viewsOverTime":[{"yearMonth":"2025-10","total":2},{"yearMonth":"2025-11","total":1}],"downloadCount":0,"downloadsOverTime":[{"yearMonth":"2025-10","total":0},{"yearMonth":"2025-11","total":0}],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2017-09-22T02:12:54.000Z","registered":"2017-09-22T02:12:54.000Z","published":"2017","updated":"2020-09-01T10:41:38.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.5432128.v2","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}