{"id":"https://openalex.org/W6967629925","doi":"https://doi.org/10.5281/zenodo.11371690","title":"ARTS Datasets - ARTS94, ARTS300, ARTS3000","display_name":"ARTS Datasets - ARTS94, ARTS300, ARTS3000","publication_year":2024,"publication_date":"2024-05-28","ids":{"openalex":"https://openalex.org/W6967629925","doi":"https://doi.org/10.5281/zenodo.11371690"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.11371690","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11371690","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":null,"license_id":null,"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.11371690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Engelmann, Bj\u00f6rn","orcid":"https://orcid.org/0009-0000-7074-9066"},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Engelmann, Bj\u00f6rn","raw_affiliation_strings":["TH K\u00f6ln - University of Applied Sciences"],"raw_orcid":"https://orcid.org/0009-0000-7074-9066","affiliations":[{"raw_affiliation_string":"TH K\u00f6ln - University of Applied Sciences","institution_ids":["https://openalex.org/I102520234"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kreutz, Christin Katharina","orcid":"https://orcid.org/0000-0002-5075-7699"},"institutions":[{"id":"https://openalex.org/I4210096970","display_name":"Herder Institute","ror":"https://ror.org/00sngv739","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210096970"]},{"id":"https://openalex.org/I45155027","display_name":"Technische Hochschule Mittelhessen","ror":"https://ror.org/02qdc9985","country_code":"DE","type":"education","lineage":["https://openalex.org/I45155027"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kreutz, Christin Katharina","raw_affiliation_strings":["Technische Hochschule Mittelhessen","Herder Institute"],"raw_orcid":"https://orcid.org/0000-0002-5075-7699","affiliations":[{"raw_affiliation_string":"Technische Hochschule Mittelhessen","institution_ids":["https://openalex.org/I45155027"]},{"raw_affiliation_string":"Herder Institute","institution_ids":["https://openalex.org/I4210096970"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haak, Fabian","orcid":"https://orcid.org/0000-0002-3392-7860"},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Haak, Fabian","raw_affiliation_strings":["TH K\u00f6ln - University of Applied Sciences"],"raw_orcid":"https://orcid.org/0000-0002-3392-7860","affiliations":[{"raw_affiliation_string":"TH K\u00f6ln - University of Applied Sciences","institution_ids":["https://openalex.org/I102520234"]}]},{"author_position":"last","author":{"id":null,"display_name":"Schaer, Philipp","orcid":"https://orcid.org/0000-0002-8817-4632"},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schaer, Philipp","raw_affiliation_strings":["Technische Hochschule K\u00f6ln"],"raw_orcid":"https://orcid.org/0000-0002-8817-4632","affiliations":[{"raw_affiliation_string":"Technische Hochschule K\u00f6ln","institution_ids":["https://openalex.org/I102520234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.8414999842643738},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.7064999938011169},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.426800012588501},{"id":"https://openalex.org/keywords/text-simplification","display_name":"Text simplification","score":0.39500001072883606},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.35179999470710754},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3257000148296356},{"id":"https://openalex.org/keywords/the-arts","display_name":"The arts","score":0.3149000108242035},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.30559998750686646}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.8414999842643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617999911308289},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.7064999938011169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5993000268936157},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5547999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48969998955726624},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C59415355","wikidata":"https://www.wikidata.org/wiki/Q3484781","display_name":"Text simplification","level":3,"score":0.39500001072883606},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C70789860","wikidata":"https://www.wikidata.org/wiki/Q2018526","display_name":"The arts","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.30559998750686646},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C18599908","wikidata":"https://www.wikidata.org/wiki/Q1196904","display_name":"Electronic publishing","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.11371690","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11371690","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.11371690","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.11371690","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Datasets":[0],"for":[1,30,52,111],"readability":[2],"and":[3,12,47,93],"text":[4,31,53,59,67,104],"simplicity":[5],"evaluation":[6],"in":[7],"three":[8],"sizes:":[9],"94,":[10],"300":[11],"3000":[13],"disjunctive":[14],"data":[15,18],"entries.":[16],"One":[17],"entry":[19],"contains":[20],"the":[21,57,66,71,79,88,95,99,103,107,112],"following":[22],"information:":[23],"Text_original:":[24],"Text":[25],"from":[26,55,70],"a":[27,97],"parallel":[28],"corpus":[29,51,80],"simplification":[32],"Text_formatted:":[33],"Text_original":[34],"where":[35],"formatting":[36],"issues":[37],"have":[38],"been":[39,61,69],"resolved":[40],"either":[41],"manually":[42],"(ARTS94)":[43],"or":[44,74],"automatically":[45],"(ARTS300":[46],"ARTS3000)":[48],"Dataset:":[49],"Parallel":[50],"simplification,":[54],"which":[56],"original":[58],"has":[60,68],"extracted":[62],"Label:":[63],"information,":[64],"if":[65],"simplified":[72],"(simp)":[73],"source":[75],"(src)":[76],"part":[77],"of":[78,87,106],"ID:":[81],"Unique":[82],"ID":[83],"Score:":[84],"Simplicity/readability":[85],"score":[86],"formatted":[89],"text,":[90],"between":[91],"0":[92],"1,":[94],"higher":[96],"score,":[98],"more":[100],"complex/less":[101],"readable":[102],"Licenses":[105],"different":[108],"datasets":[109],"apply":[110],"respective":[113],"texts.":[114]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
