{"id":"https://openalex.org/W4393520665","doi":"https://doi.org/10.5281/zenodo.10013755","title":"MULTITuDE","display_name":"MULTITuDE","publication_year":2023,"publication_date":"2023-10-17","ids":{"openalex":"https://openalex.org/W4393520665","doi":"https://doi.org/10.5281/zenodo.10013755"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10013755","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10013755","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10013755","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079722422","display_name":"Dominik Macko","orcid":"https://orcid.org/0000-0002-8235-2004"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Macko, Dominik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032021797","display_name":"R\u00f3bert M\u00f3ro","orcid":"https://orcid.org/0000-0002-3052-8290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moro, Robert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075543864","display_name":"Adaku Uchendu","orcid":"https://orcid.org/0000-0001-7437-5153"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uchendu, Adaku","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060378653","display_name":"Jason Samuel Lucas","orcid":"https://orcid.org/0009-0000-3494-6935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas, Jason Samuel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006093397","display_name":"Michiharu Yamashita","orcid":"https://orcid.org/0009-0002-3802-8618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamashita, Michiharu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042084033","display_name":"Mat\u00fa\u0161 Pikuliak","orcid":"https://orcid.org/0000-0003-1353-9462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pikuliak, Mat\u00fa\u0161","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082763244","display_name":"Ivan Srba","orcid":"https://orcid.org/0000-0003-3511-5337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srba, Ivan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039440984","display_name":"Thai Le","orcid":"https://orcid.org/0000-0001-9632-6870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Thai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Dongwon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043199710","display_name":"Jakub \u0160imko","orcid":"https://orcid.org/0000-0003-0239-4237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simko, Jakub","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030414237","display_name":"M\u00e1ria Bielikov\u00e1","orcid":"https://orcid.org/0000-0003-4105-3494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bielikova, Maria","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5079722422"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.896399974822998,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.896399974822998,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.848800003528595,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899086236953735},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5962868928909302},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5860414505004883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5516524910926819},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4838468134403229},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44237440824508667},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17763358354568481},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16004464030265808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899086236953735},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5962868928909302},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5860414505004883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5516524910926819},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4838468134403229},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44237440824508667},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17763358354568481},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16004464030265808},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10013755","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10013755","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10013755","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10013755","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2046765700","https://openalex.org/W4384345686","https://openalex.org/W2357937784","https://openalex.org/W2547618384","https://openalex.org/W2145834781","https://openalex.org/W2577782152","https://openalex.org/W262455470","https://openalex.org/W4242899858","https://openalex.org/W3204019825","https://openalex.org/W2296205523"],"abstract_inverted_index":{"MULTITuDE":[0],"is":[1],"a":[2,56,87,102,105,118,123,165],"dataset":[3,63,80,132,170],"for":[4,51,93,97,133],"multilingual":[5],"machine-generated":[6,98],"text":[7,88,112],"detection":[8],"benchmark,":[9],"described":[10],"in":[11,24,55,64,70],"the":[12,76,82,111,114,131,134,143,149,152,160,168,175],"EMNLP":[13],"2023":[14],"conference":[15],"paper.":[16,77],"It":[17],"consists":[18],"of":[19,43,130,136,151,159,174,181],"7992":[20,194,226],"human-written":[21,94,119],"news":[22,44,172],"texts":[23,33],"11":[25],"languages":[26],"subsampled":[27],"from":[28],"MassiveSumm,":[29],"accompanied":[30],"by":[31,35],"66089":[32,197],"generated":[34,110],"8":[36],"large":[37,106],"language":[38,107,146,150],"models":[39],"(by":[40],"using":[41],"headlines":[42],"articles).":[45],"The":[46,79],"creation":[47],"process":[48],"and":[49,138],"scripts":[50],"replication/extension":[52],"are":[53],"located":[54],"GitHub":[57],"repository.":[58],"If":[59],"you":[60],"use":[61],"this":[62],"any":[65,71],"publication,":[66],"project,":[67],"tool":[68],"or":[69,113,127],"other":[72],"form,":[73],"please,":[74],"cite":[75],"Fields":[78],"has":[81],"following":[83],"fields:":[84],"'text'":[85],"-":[86,91,101,122,142,156,164,185,188,193,196,201,204,207,210,213,216,219,222,225,230,237,244,251,256,261,266,271,276,281,286],"sample,":[89],"'label'":[90],"0":[92,192],"text,":[95,99,120,154,162],"1":[96,195],"'multi_label'":[100],"string":[103,115,124,166],"representing":[104,117],"model":[108],"that":[109],"\"human\"":[116],"'split'":[121],"identifying":[125,148,167],"train":[126,184],"test":[128,187],"split":[129],"purpose":[135],"training":[137],"evaluation":[139],"respectively,":[140],"'language'":[141],"ISO":[144],"639-1":[145],"code":[147],"given":[153,161,176],"'length'":[155],"word":[157],"count":[158],"'source'":[163],"source":[169],"/":[171],"medium":[173],"text.":[177],"Statistics":[178],"(the":[179],"number":[180],"samples)":[182],"Splits:":[183],"44786":[186],"29295":[189],"Binary":[190],"labels:":[191,199],"Multiclass":[198],"gpt-3.5-turbo":[200],"8300":[202,205],"gpt-4":[203],"text-davinci-003":[206],"8297":[208],"alpaca-lora-30b":[209],"8290":[211],"vicuna-13b":[212],"8287":[214],"opt-66b":[215],"8229":[217,220],"llama-65b":[218],"opt-iml-max-1.3b":[221],"8157":[223],"human":[224],"Languages:":[227],"English":[228],"(en)":[229],"29460":[231],"(train":[232,239,246],"+":[233,240,247],"test)":[234,241,248],"Spanish":[235],"(es)":[236],"11586":[238],"Russian":[242],"(ru)":[243],"11578":[245],"Dutch":[249],"(nl)":[250],"2695":[252],"(test)":[253,258,263,268,273,278,283,288],"Catalan":[254],"(ca)":[255],"2691":[257],"Czech":[259],"(cs)":[260],"2689":[262],"German":[264],"(de)":[265],"2685":[267],"Chinese":[269],"(zh)":[270],"2683":[272],"Portuguese":[274],"(pt)":[275],"2673":[277,282],"Arabic":[279],"(ar)":[280],"Ukrainian":[284],"(uk)":[285],"2668":[287]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2024-04-03T00:00:00"}
