{"id":"https://openalex.org/W6930831730","doi":"https://doi.org/10.5281/zenodo.15647143","title":"Catalan and Spanish Lexical Simplification and Complexity Prediction Dataset","display_name":"Catalan and Spanish Lexical Simplification and Complexity Prediction Dataset","publication_year":2025,"publication_date":"2025-06-12","ids":{"openalex":"https://openalex.org/W6930831730","doi":"https://doi.org/10.5281/zenodo.15647143"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15647143","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15647143","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.15647143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bott, Stefan","orcid":"https://orcid.org/0009-0002-7365-9482"},"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":"Bott, Stefan","raw_affiliation_strings":["Pompeu Fabra University"],"raw_orcid":"https://orcid.org/0009-0002-7365-9482","affiliations":[{"raw_affiliation_string":"Pompeu Fabra University","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":null,"display_name":"Saggion, Horacio","orcid":"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":"Saggion, Horacio","raw_affiliation_strings":["Pompeu Fabra University"],"raw_orcid":"https://orcid.org/0000-0003-0016-7807","affiliations":[{"raw_affiliation_string":"Pompeu Fabra University","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":{"id":"https://openalex.org/T10250","display_name":"Glaucoma and retinal disorders","score":0.36399999260902405,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10250","display_name":"Glaucoma and retinal disorders","score":0.36399999260902405,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10170","display_name":"Retinal Diseases and Treatments","score":0.10339999943971634,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11538","display_name":"Ophthalmology and Eye Disorders","score":0.046300001442432404,"subfield":{"id":"https://openalex.org/subfields/2734","display_name":"Pathology and Forensic Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/catalan","display_name":"Catalan","score":0.9229000210762024},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6212999820709229},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5291000008583069},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5040000081062317},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4959999918937683},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.48660001158714294},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44850000739097595},{"id":"https://openalex.org/keywords/lexical-database","display_name":"Lexical database","score":0.44110000133514404}],"concepts":[{"id":"https://openalex.org/C164105321","wikidata":"https://www.wikidata.org/wiki/Q7026","display_name":"Catalan","level":2,"score":0.9229000210762024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366999983787537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6930000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6531999707221985},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C2780403423","wikidata":"https://www.wikidata.org/wiki/Q6537700","display_name":"Lexical database","level":3,"score":0.44110000133514404},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15647143","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15647143","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.15647143","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15647143","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":0.5065193176269531,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"is":[1,323],"the":[2,5,9,23,33,51,67,107,115,175,180,189,220,225,256,261,290,318,336,343,370,375],"Spanish":[3,54,236],"and":[4,15,46,55,72,167,258,274,279,285,297,380],"Catalan":[6,56,118,201,278],"part":[7],"of":[8,37,50,69,109,127,144,204,224,232,239,260,289,317,342,349,374],"MLSP":[10,24,320],"dataset":[11,202,237],"on":[12,153,156,248,251,255,293,335,346,378],"Lexical":[13,16,26,154,275,338,365],"Simplification":[14,27,276,339,366],"Complexity":[17,155,272],"Prediction.":[18],"They":[19],"were":[20,62,100,133,184,217],"used":[21],"in":[22,85,179,243],"(Multilingual":[25],"Pipeline)":[28],"shared":[29],"task,":[30],"held":[31],"at":[32],"BEA":[34,319,331],"(Innovative":[35],"use":[36],"NLP":[38,350],"for":[39,53,102,117,146,174,277,308,351,382],"Building":[40,352],"Educational":[41,221,353],"Applications).":[42],"The":[43,74,138,200,235,315],"target":[44,81,124,148,176,190,210,241],"selection":[45],"data":[47,145],"collection":[48],"process":[49,140],"datasets":[52,262],"was":[57,77,130],"largely":[58],"parallel,":[59],"but":[60],"there":[61],"some":[63],"differences":[64],"due":[65],"to":[66,78,106,113,119,164,170,186],"availability":[68],"source":[70],"texts":[71,247],"annotators.":[73],"initial":[75],"goal":[76,116],"select":[79],"600":[80],"words":[82,242],"per":[83,91],"language":[84],"200":[86],"contexts,":[87],"with":[88,384],"3":[89,171],"targets":[90],"context.":[92,182],"An":[93],"additional":[94],"10":[95,128],"contexts":[96,245],"(and":[97],"30":[98],"words)":[99],"required":[101,131],"pilot":[103],"annotations.":[104],"Due":[105],"sparseness":[108],"resources,":[110],"we":[111],"had":[112],"relax":[114],"160":[120,205],"contexts.":[121],"For":[122],"each":[123,147],"a":[125,151,157,197],"minimum":[126],"annotations":[129],"which":[132],"collected":[134,141],"through":[135],"on-line":[136],"forms.":[137],"annotation":[139],"two":[142],"pieces":[143],"word:":[149],"i)":[150],"rating":[152],"5-point":[158],"Likert":[159],"scale":[160],"(from":[161],"\"very":[162,165],"easy\"":[163],"hard\")":[166],"ii)":[168],"up":[169],"lexical":[172],"substitutes":[173],"that":[177],"fit":[178],"given":[181],"Annotators":[183],"asked":[185],"simply":[187],"repeat":[188],"word":[191,211],"if":[192],"they":[193],"could":[194],"not":[195],"find":[196],"suitable":[198],"alternative.":[199],"consists":[203,238],"context":[206],"sentences":[207],"containing":[208],"475":[209],"tokens":[212],"(454":[213],"distinct":[214],"types).":[215],"Sentences":[216],"selected":[218],"from":[219,246],"news":[222,233],"section":[223],"TeCla":[226],"corpus4":[227],"(Armengol-Estap\u00e9":[228],"et":[229,269,305,328,359],"al.,":[230,306],"2021)":[231],"texts.":[234],"625":[240],"210":[244],"educational":[249],"books":[250],"finance.":[252],"More":[253],"details":[254],"creation":[257],"compositoin":[259],"can":[263],"be":[264],"found":[265],"in:":[266,325],"Saggion,":[267],"Horacio,":[268],"al.":[270,329,360],"\u2018Lexical":[271],"Prediction":[273],"Spanish:":[280],"Resource":[281],"Creation,":[282],"Quality":[283],"Assessment,":[284],"Ethical":[286],"Considerations\u2019.":[287],"Proceedings":[288,341,373],"Third":[291],"Workshop":[292,345,377],"Text":[294],"Simplification,":[295],"Accessibility":[296],"Readability":[298],"(TSAR":[299],"2024),":[300],"edited":[301],"by":[302],"Matthew":[303],"Shardlow":[304],"Association":[307],"Computational":[309],"Linguistics,":[310],"2024,":[311],"pp.":[312],"82\u201394,":[313],"https://aclanthology.org/2024.tsar-1.9.":[314],"description":[316],"Shared":[321,333],"task":[322],"described":[324],"Shardlow,":[326,357],"Matthew,":[327,358],"\u2018The":[330],"2024":[332],"Task":[334],"Multilingual":[337,364],"Pipeline\u2019.":[340],"19th":[344],"Innovative":[347],"Use":[348],"Applications":[354],"(BEA),":[355],"2024.":[356,388],"\u2018An":[361],"Extensible":[362],"Massively":[363],"Pipeline":[367],"Dataset":[368],"Using":[369],"MultiLS":[371],"Framework\u2019.":[372],"3rd":[376],"Tools":[379],"Resources":[381],"People":[383],"Reading":[385],"Difficulties":[386],"(READI),":[387]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
