{"id":"https://openalex.org/W7204926041","doi":"https://doi.org/10.1016/j.dib.2026.113217","title":"A step toward inclusion: A transparent dataset for automatic text simplification for screen reader users","display_name":"A step toward inclusion: A transparent dataset for automatic text simplification for screen reader users","publication_year":2026,"publication_date":"2026-08-01","ids":{"openalex":"https://openalex.org/W7204926041","doi":"https://doi.org/10.1016/j.dib.2026.113217","pmid":"https://pubmed.ncbi.nlm.nih.gov/42774625"},"language":"en","primary_location":{"id":"doi:10.1016/j.dib.2026.113217","doi":"https://doi.org/10.1016/j.dib.2026.113217","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2026.113217","pdf_url":"https://www.sciencedirect.com/science/article/pii/S235234092600764X/pdf","source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},"volume":null,"type":"data-paper","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.sciencedirect.com/science/article/pii/S235234092600764X/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089698734","display_name":"Nelson P\u00e9rez Rojas","orcid":"https://orcid.org/0000-0001-8929-3249","observed_orcids":["https://orcid.org/0000-0001-8929-3249"]},"institutions":[{"id":"https://openalex.org/I145372079","display_name":"Instituto Tecnol\u00f3gico de Costa Rica","ror":"https://ror.org/04zhrfn38","country_code":"CR","type":"education","lineage":["https://openalex.org/I145372079"]},{"id":"https://openalex.org/I3130757197","display_name":"Distance State University","ror":"https://ror.org/0529rbt18","country_code":"CR","type":"education","lineage":["https://openalex.org/I3130757197"]}],"countries":["CR"],"is_corresponding":true,"raw_author_name":"Nelson P\u00e9rez-Rojas","raw_affiliation_strings":["Doctorado en Ciencias Naturales para el Desarrollo (DOCINADE), Instituto Tecnol\u00f3gico de Costa Rica, Universidad Nacional, Universidad Estatal a Distancia, Cartago, Costa Rica"],"raw_orcid":"https://orcid.org/0000-0001-8929-3249","affiliations":[{"raw_affiliation_string":"Doctorado en Ciencias Naturales para el Desarrollo (DOCINADE), Instituto Tecnol\u00f3gico de Costa Rica, Universidad Nacional, Universidad Estatal a Distancia, Cartago, Costa Rica","institution_ids":["https://openalex.org/I145372079","https://openalex.org/I3130757197"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135342488","display_name":"Mart\u00edn Sol\u00eds","orcid":"https://orcid.org/0000-0003-4750-1198","observed_orcids":["https://orcid.org/0000-0003-4750-1198"]},"institutions":[{"id":"https://openalex.org/I145372079","display_name":"Instituto Tecnol\u00f3gico de Costa Rica","ror":"https://ror.org/04zhrfn38","country_code":"CR","type":"education","lineage":["https://openalex.org/I145372079"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Mart\u00edn Sol\u00eds","raw_affiliation_strings":["Instituto Tecnol\u00f3gico de Costa Rica, Cartago, Costa Rica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Tecnol\u00f3gico de Costa Rica, Cartago, Costa Rica","institution_ids":["https://openalex.org/I145372079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128887764","display_name":"Sa\u00fal Calder\u00f3n-Ram\u00edrez","orcid":"https://orcid.org/0000-0001-9993-4388","observed_orcids":["https://orcid.org/0000-0001-9993-4388"]},"institutions":[{"id":"https://openalex.org/I145372079","display_name":"Instituto Tecnol\u00f3gico de Costa Rica","ror":"https://ror.org/04zhrfn38","country_code":"CR","type":"education","lineage":["https://openalex.org/I145372079"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Sa\u00fal Calder\u00f3n-Ram\u00edrez","raw_affiliation_strings":["Instituto Tecnol\u00f3gico de Costa Rica, Cartago, Costa Rica"],"raw_orcid":"https://orcid.org/0000-0001-9993-4388","affiliations":[{"raw_affiliation_string":"Instituto Tecnol\u00f3gico de Costa Rica, Cartago, Costa Rica","institution_ids":["https://openalex.org/I145372079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093524926","display_name":"Monica Arias-Monge","orcid":"https://orcid.org/0000-0003-0836-0775","observed_orcids":["https://orcid.org/0000-0003-0836-0775"]},"institutions":[{"id":"https://openalex.org/I31944674","display_name":"Universidad de Costa Rica","ror":"https://ror.org/02yzgww51","country_code":"CR","type":"education","lineage":["https://openalex.org/I31944674"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"M\u00f3nica Arias-Monge","raw_affiliation_strings":["Universidad de Costa Rica, San Jos\u00e9, Costa Rica"],"raw_orcid":"https://orcid.org/0000-0003-0836-0775","affiliations":[{"raw_affiliation_string":"Universidad de Costa Rica, San Jos\u00e9, Costa Rica","institution_ids":["https://openalex.org/I31944674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046825099","display_name":"Horacio Saggion","orcid":"https://orcid.org/0000-0003-0016-7807","observed_orcids":["https://orcid.org/0000-0003-0016-7807"]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Horacio Saggion","raw_affiliation_strings":["Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0016-7807","affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092370541","display_name":"Danny Xie-Li","orcid":"https://orcid.org/0000-0003-1878-9460","observed_orcids":["https://orcid.org/0000-0003-1878-9460"]},"institutions":[{"id":"https://openalex.org/I145372079","display_name":"Instituto Tecnol\u00f3gico de Costa Rica","ror":"https://ror.org/04zhrfn38","country_code":"CR","type":"education","lineage":["https://openalex.org/I145372079"]},{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["CR","LU"],"is_corresponding":false,"raw_author_name":"Danny Xie-Li","raw_affiliation_strings":["Instituto Tecnol\u00f3gico de Costa Rica, Cartago, Costa Rica","Universit\u00e9 du Luxembourg, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0003-1878-9460","affiliations":[{"raw_affiliation_string":"Instituto Tecnol\u00f3gico de Costa Rica, Cartago, Costa Rica","institution_ids":["https://openalex.org/I145372079"]},{"raw_affiliation_string":"Universit\u00e9 du Luxembourg, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089698734"],"corresponding_institution_ids":["https://openalex.org/I145372079","https://openalex.org/I3130757197"],"apc_list":{"value":1220,"currency":"USD","value_usd":1220},"apc_paid":{"value":1220,"currency":"USD","value_usd":1220},"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":null,"first_page":"113217","last_page":"113217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9994999766349792,"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/T13629","display_name":"Text Readability and Simplification","score":0.9994999766349792,"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":0.00019999999494757503,"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/T12481","display_name":"Digital Accessibility for Disabilities","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3307","display_name":"Human Factors and Ergonomics"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-simplification","display_name":"text simplification","score":0.9950000047683716},{"id":"https://openalex.org/keywords/screen-readers","display_name":"screen readers","score":0.8859999775886536},{"id":"https://openalex.org/keywords/blind-and-visually-impaired-users","display_name":"blind and visually impaired users","score":0.9259999990463257},{"id":"https://openalex.org/keywords/spanish-language-texts","display_name":"Spanish-language texts","score":0.5440000295639038},{"id":"https://openalex.org/keywords/accessibility","display_name":"accessibility","score":0.4690000116825104},{"id":"https://openalex.org/keywords/annotation-guidelines","display_name":"annotation guidelines","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404999732971191},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37059998512268066},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C3018127295","wikidata":"https://www.wikidata.org/wiki/Q5246046","display_name":"Research article","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.2721000015735626}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.dib.2026.113217","doi":"https://doi.org/10.1016/j.dib.2026.113217","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2026.113217","pdf_url":"https://www.sciencedirect.com/science/article/pii/S235234092600764X/pdf","source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},{"id":"pmid:42774625","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42774625","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in brief","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13594948","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13594948/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13594948/pdf/main.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Brief","raw_type":"Text"},{"id":"pmh:oai:repositori.upf.edu:10230/74682","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10230/74682","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.dib.2026.113217","doi":"https://doi.org/10.1016/j.dib.2026.113217","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2026.113217","pdf_url":"https://www.sciencedirect.com/science/article/pii/S235234092600764X/pdf","source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323280","display_name":"Instituto Tecnol\u00f3gico de Costa Rica","ror":"https://ror.org/04zhrfn38"},{"id":"https://openalex.org/F4320336913","display_name":"Vicerrector\u00eda de Investigaci\u00f3n y Extensi\u00f3n, Universidad Industrial de Santander","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204926041.pdf","grobid_xml":"https://content.openalex.org/works/W7204926041.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1996445490","https://openalex.org/W2534253848","https://openalex.org/W3086436675","https://openalex.org/W4367310362","https://openalex.org/W4410226674"],"related_works":[],"abstract_inverted_index":{"GeoSimp":[0,247],"is":[1,171,241,248,270,309],"a":[2,73,83,123,149,163,285,313],"Spanish-language":[3,38],"dataset":[4,22,170,269,308],"for":[5,40,250,256,263,275],"automatic":[6],"text":[7,41,44,141,258],"simplification":[8,42,235,274],"(ATS),":[9],"comprising":[10,185,218],"approximately":[11],"3200":[12],"discourse":[13,116,188,221],"segments":[14,117],"derived":[15],"from":[16,63],"peer-reviewed":[17],"geological":[18],"scientific":[19,56],"articles.":[20],"The":[21,169,177,210,268,292,307],"was":[23,95],"constructed":[24],"to":[25,98,158],"address":[26],"two":[27,174],"documented":[28],"gaps":[29],"in":[30,66,127,134,140,244,288,312],"existing":[31],"ATS":[32,254,290],"resources:":[33],"the":[34,48,67,121,186,193,196,200,204,207,219,245,289],"limited":[35],"availability":[36],"of":[37,50,78,120,152,206,295],"corpora":[39],"and":[43,47,112,137,146,166,203,223,252,262,277,303],"complexity":[45,155,198,259,297],"classification,":[46],"scarcity":[49],"domain-specific":[51],"datasets":[52],"focused":[53],"on":[54,265,282],"specialized":[55],"writing.":[57],"Source":[58],"texts":[59],"were":[60,103],"drawn":[61],"exclusively":[62],"articles":[64],"published":[65],"Revista":[68],"Geol\u00f3gica":[69],"de":[70],"Am\u00e9rica":[71],"Central,":[72],"peer-reviewed,":[74],"open-access":[75],"journal,":[76],"all":[77],"which":[79],"are":[80],"distributed":[81,172],"under":[82],"single":[84],"Creative":[85],"Commons":[86],"Attribution-NonCommercial-ShareAlike":[87],"3.0":[88],"(CC":[89],"BY-NC-SA":[90],"3.0)":[91],"license.":[92],"Text":[93],"extraction":[94],"performed":[96,143],"manually":[97],"preserve":[99],"structural":[100],"coherence.":[101],"Paragraphs":[102],"copied":[104],"into":[105,115],"Microsoft":[106],"Excel":[107,175],"spreadsheets,":[108],"assigned":[109],"unique":[110],"identifiers,":[111],"subsequently":[113],"segmented":[114],"by":[118],"one":[119,190],"authors,":[122],"researcher":[124],"with":[125,131,229],"expertise":[126],"linguistics.":[128],"Four":[129],"annotators":[130,161],"university":[132],"degrees":[133],"Spanish":[135],"philology":[136],"professional":[138],"experience":[139],"editing":[142],"attribute":[144,232],"identification":[145],"simplification,":[147],"using":[148],"predefined":[150],"scheme":[151],"21":[153],"linguistic":[154,296],"attributes.":[156],"Prior":[157],"annotation,":[159],"these":[160],"completed":[162],"structured":[164],"training":[165,178,251],"calibration":[167],"phase.":[168],"as":[173],"files.":[176],"file":[179,212],"(GeoSimp_train.xlsx)":[180],"contains":[181,214],"2956":[182],"records,":[183,216],"each":[184,217],"original":[187,220],"segment,":[189],"simplified":[191,227],"version,":[192],"annotator":[194],"identifier,":[195,202],"identified":[197],"attributes,":[199],"paragraph":[201],"identifier":[205],"source":[208],"article.":[209],"test":[211],"(GeoSimp_test.xlsx)":[213],"301":[215],"segment":[222,300],"four":[224],"independently":[225],"produced":[226],"versions":[228],"their":[230],"corresponding":[231],"annotations.":[233],"A":[234],"guidelines":[236],"manual":[237],"used":[238],"during":[239],"annotation":[240,294],"also":[242],"included":[243],"repository.":[246,316],"suitable":[249],"evaluating":[253],"models,":[255,261],"developing":[257],"classification":[260],"research":[264],"paragraph-level":[266],"simplification.":[267],"specifically":[271],"oriented":[272],"toward":[273],"blind":[276],"low-vision":[278],"users":[279],"who":[280],"rely":[281],"screen":[283],"readers,":[284],"population":[286],"underrepresented":[287],"literature.":[291],"explicit":[293],"attributes":[298],"per":[299],"supports":[301],"reproducibility":[302],"fine-grained":[304],"error":[305],"analysis.":[306],"openly":[310],"available":[311],"public":[314],"GitHub":[315]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-09-02T00:00:00"}
