{"id":"https://openalex.org/W6944660023","doi":"https://doi.org/10.21227/2yex-bt23","title":"SciBank: A Large Dataset of Annotated Scientific Paper Regions for Document Layout Analysis","display_name":"SciBank: A Large Dataset of Annotated Scientific Paper Regions for Document Layout Analysis","publication_year":2022,"publication_date":"2022-03-14","ids":{"openalex":"https://openalex.org/W6944660023","doi":"https://doi.org/10.21227/2yex-bt23"},"language":"en","primary_location":{"id":"doi:10.21227/2yex-bt23","is_oa":true,"landing_page_url":"https://doi.org/10.21227/2yex-bt23","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/10.21227/2yex-bt23","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Grijalva, Felipe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102282","display_name":"Universidad de Las Am\u00e9ricas","ror":"https://ror.org/0198j4566","country_code":"EC","type":"education","lineage":["https://openalex.org/I4210102282"]},{"id":"https://openalex.org/I4210104854","display_name":"National Polytechnic School","ror":null,"country_code":"EC","type":null,"lineage":["https://openalex.org/I4210104854"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Grijalva, Felipe","raw_affiliation_strings":["Escuela Polit\u00e9cnica Nacional (Quito, Ecuador) and Faculty of Engineering and Applied Sciences (FICA), Telecommunications Engineering, Universidad de Las Am\u00e9ricas (UDLA), Quito 170125, Ecuador"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela Polit\u00e9cnica Nacional (Quito, Ecuador) and Faculty of Engineering and Applied Sciences (FICA), Telecommunications Engineering, Universidad de Las Am\u00e9ricas (UDLA), Quito 170125, Ecuador","institution_ids":["https://openalex.org/I4210102282","https://openalex.org/I4210104854"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Parra, Carla","orcid":null},"institutions":[{"id":"https://openalex.org/I173713965","display_name":"Institut Barcelona d'Estudis Internacionals","ror":"https://ror.org/05rke5d69","country_code":"ES","type":"education","lineage":["https://openalex.org/I173713965","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Parra, Carla","raw_affiliation_strings":["NuCom, Nuevas Comunicaciones Iberia S.A., Barcelona, 08172, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NuCom, Nuevas Comunicaciones Iberia S.A., Barcelona, 08172, Spain","institution_ids":["https://openalex.org/I173713965"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gallardo, Marco","orcid":null},"institutions":[{"id":"https://openalex.org/I70764802","display_name":"National Polytechnic School","ror":"https://ror.org/01gb99w41","country_code":"EC","type":"education","lineage":["https://openalex.org/I70764802"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Gallardo, Marco","raw_affiliation_strings":["Escuela Polit\u00e9cnica Nacional (Quito, Ecuador)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela Polit\u00e9cnica Nacional (Quito, Ecuador)","institution_ids":["https://openalex.org/I70764802"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Santos, Erick","orcid":null},"institutions":[{"id":"https://openalex.org/I70764802","display_name":"National Polytechnic School","ror":"https://ror.org/01gb99w41","country_code":"EC","type":"education","lineage":["https://openalex.org/I70764802"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Santos, Erick","raw_affiliation_strings":["Escuela Polit\u00e9cnica Nacional (Quito, Ecuador)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela Polit\u00e9cnica Nacional (Quito, Ecuador)","institution_ids":["https://openalex.org/I70764802"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Acu\u00f1a, Byron","orcid":null},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Acu\u00f1a, Byron","raw_affiliation_strings":["University of Campinas UNICAMP (Campinas, Brazil)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Campinas UNICAMP (Campinas, Brazil)","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rodr\u00edguez, Juan Carlos","orcid":null},"institutions":[{"id":"https://openalex.org/I117023288","display_name":"Analog Devices (United States)","ror":"https://ror.org/01545pm61","country_code":"US","type":"company","lineage":["https://openalex.org/I117023288"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rodr\u00edguez, Juan Carlos","raw_affiliation_strings":["Interface and Isolation Products Group, Analog Devices Incorporated, Wilmington, MA 01887 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interface and Isolation Products Group, Analog Devices Incorporated, Wilmington, MA 01887 USA","institution_ids":["https://openalex.org/I117023288"]}]},{"author_position":"last","author":{"id":null,"display_name":"Larco, Julio","orcid":null},"institutions":[{"id":"https://openalex.org/I118946981","display_name":"Universidad de las Fuerzas Armadas ESPE","ror":"https://ror.org/05j136930","country_code":"EC","type":"education","lineage":["https://openalex.org/I118946981"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Larco, Julio","raw_affiliation_strings":["Departamento de El\u00e9ctrica, Electr\u00f3nica y Telecomunicaciones, Universidad de las Fuerzas Armadas ESPE, Sangolqu\u00ed - Ecuador"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de El\u00e9ctrica, Electr\u00f3nica y Telecomunicaciones, Universidad de las Fuerzas Armadas ESPE, Sangolqu\u00ed - Ecuador","institution_ids":["https://openalex.org/I118946981"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/context","display_name":"Context (archaeology)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/inclusion","display_name":"Inclusion (mineral)","score":0.39070001244544983},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.388700008392334},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.3779999911785126},{"id":"https://openalex.org/keywords/source-document","display_name":"Source document","score":0.34470000863075256},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.27559998631477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132999897003174},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6003999710083008},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4636000096797943},{"id":"https://openalex.org/C109359841","wikidata":"https://www.wikidata.org/wiki/Q728944","display_name":"Inclusion (mineral)","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C105888452","wikidata":"https://www.wikidata.org/wiki/Q7565148","display_name":"Source document","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C2778864079","wikidata":"https://www.wikidata.org/wiki/Q173285","display_name":"Digital data","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/2yex-bt23","is_oa":true,"landing_page_url":"https://doi.org/10.21227/2yex-bt23","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:10.21227/2yex-bt23","is_oa":true,"landing_page_url":"https://doi.org/10.21227/2yex-bt23","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"score":0.6556426286697388,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Document":[0,22],"layout":[1],"analysis":[2],"(DLA)":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"for":[8],"identifying":[9],"and":[10,51,55,105],"classifying":[11],"the":[12,19,96,117],"different":[13],"regions":[14,69],"of":[15,21,27,36,58,119],"digital":[16],"documents":[17],"in":[18,82],"context":[20],"Understanding":[23],"tasks.":[24],"In":[25],"light":[26],"this,":[28],"SciBank":[29,74],"seeks":[30],"to":[31],"provide":[32],"a":[33],"considerable":[34],"amount":[35],"data":[37],"from":[38,78],"text":[39,41],"(abstract,":[40],"blocks,":[42],"caption,":[43],"keywords,":[44],"reference,":[45],"section,":[46],"subsection,":[47],"title),":[48],"tables,":[49],"figures":[50],"equations":[52,54],"(isolated":[53],"inline":[56,120],"equations)":[57],"74435":[59],"scientific":[60],"articles":[61],"pages.":[62],"Human":[63],"curators":[64],"validated":[65],"that":[66],"these":[67,109],"12":[68],"were":[70],"properly":[71],"labeled.":[72],"Moreover,":[73],"offers":[75],"relevant":[76],"information":[77],"unstructured":[79],"data,":[80],"which":[81],"turn":[83],"might":[84],"be":[85],"used":[86],"later":[87],"by":[88],"machine":[89],"learning":[90],"models.":[91],"We":[92],"aim":[93],"at":[94],"complementing":[95],"current":[97],"DLA":[98],"datasets":[99],"available":[100,111],"such":[101],"as":[102],"Publaynet,":[103],"TableBank,":[104],"DocBank.":[106],"Different":[107],"than":[108],"publicly":[110],"datasets,":[112],"our":[113],"main":[114],"contributions":[115],"is":[116],"inclusion":[118],"equation":[121],"annotated":[122],"regions.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
