{"id":"https://openalex.org/W4404459606","doi":"https://doi.org/10.1007/s00521-024-10662-9","title":"Deep Encodings vs. Linguistic Features in Lexical Complexity Prediction","display_name":"Deep Encodings vs. Linguistic Features in Lexical Complexity Prediction","publication_year":2024,"publication_date":"2024-11-18","ids":{"openalex":"https://openalex.org/W4404459606","doi":"https://doi.org/10.1007/s00521-024-10662-9"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-024-10662-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-024-10662-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10662-9.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10662-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036470713","display_name":"Jenny Ortiz Zambrano","orcid":"https://orcid.org/0000-0001-6708-4470"},"institutions":[{"id":"https://openalex.org/I2405095","display_name":"University of Guayaquil","ror":"https://ror.org/047kyg834","country_code":"EC","type":"education","lineage":["https://openalex.org/I2405095"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Jenny A. Ortiz-Zambrano","raw_affiliation_strings":["Facultad de Ciencias Matem\u00e1ticas y F\u00edsicas, Universidad de Guayaquil, Av. Delta S/N, 090514, Guayaquil, Ecuador"],"raw_orcid":"https://orcid.org/0000-0001-6708-4470","affiliations":[{"raw_affiliation_string":"Facultad de Ciencias Matem\u00e1ticas y F\u00edsicas, Universidad de Guayaquil, Av. Delta S/N, 090514, Guayaquil, Ecuador","institution_ids":["https://openalex.org/I2405095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069207433","display_name":"C\u00e9sar Esp\u00edn-Riofrio","orcid":"https://orcid.org/0000-0001-8864-756X"},"institutions":[{"id":"https://openalex.org/I2405095","display_name":"University of Guayaquil","ror":"https://ror.org/047kyg834","country_code":"EC","type":"education","lineage":["https://openalex.org/I2405095"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"C\u00e9sar H. Esp\u00edn-Riofr\u00edo","raw_affiliation_strings":["Facultad de Ciencias Matem\u00e1ticas y F\u00edsicas, Universidad de Guayaquil, Av. Delta S/N, 090514, Guayaquil, Ecuador"],"raw_orcid":"https://orcid.org/0000-0001-8864-756X","affiliations":[{"raw_affiliation_string":"Facultad de Ciencias Matem\u00e1ticas y F\u00edsicas, Universidad de Guayaquil, Av. Delta S/N, 090514, Guayaquil, Ecuador","institution_ids":["https://openalex.org/I2405095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015449918","display_name":"Arturo Montejo\u2010R\u00e1ez","orcid":"https://orcid.org/0000-0002-8643-2714"},"institutions":[{"id":"https://openalex.org/I191420491","display_name":"Universidad de Ja\u00e9n","ror":"https://ror.org/0122p5f64","country_code":"ES","type":"education","lineage":["https://openalex.org/I191420491"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Arturo Montejo-R\u00e1ez","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad de Ja\u00e9n, Ja\u00e9n, 23071, Las Lagunillas S/N, Spain"],"raw_orcid":"https://orcid.org/0000-0002-8643-2714","affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad de Ja\u00e9n, Ja\u00e9n, 23071, Las Lagunillas S/N, Spain","institution_ids":["https://openalex.org/I191420491"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015449918"],"corresponding_institution_ids":["https://openalex.org/I191420491"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.6623,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76184894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"37","issue":"3","first_page":"1171","last_page":"1187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9945999979972839,"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/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.8925977945327759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5751122236251831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5534369349479675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5291978120803833},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.5209987759590149},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4847559630870819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19857454299926758},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12411817908287048}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.8925977945327759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5751122236251831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5534369349479675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5291978120803833},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.5209987759590149},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4847559630870819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19857454299926758},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12411817908287048}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-024-10662-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-024-10662-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10662-9.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-024-10662-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-024-10662-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10662-9.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5665229100","display_name":null,"funder_award_id":"1380939","funder_id":"https://openalex.org/F4320321562","funder_display_name":"Consejer\u00eda de Econom\u00eda, Innovaci\u00f3n, Ciencia y Empleo, Junta de Andaluc\u00eda"},{"id":"https://openalex.org/G6114690397","display_name":null,"funder_award_id":"P20_00956","funder_id":"https://openalex.org/F4320321562","funder_display_name":"Consejer\u00eda de Econom\u00eda, Innovaci\u00f3n, Ciencia y Empleo, Junta de Andaluc\u00eda"}],"funders":[{"id":"https://openalex.org/F4320321562","display_name":"Consejer\u00eda de Econom\u00eda, Innovaci\u00f3n, Ciencia y Empleo, Junta de Andaluc\u00eda","ror":"https://ror.org/03kak1729"},{"id":"https://openalex.org/F4320324132","display_name":"Universidad de Ja\u00e9n","ror":"https://ror.org/0122p5f64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404459606.pdf","grobid_xml":"https://content.openalex.org/works/W4404459606.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2055518963","https://openalex.org/W2087388117","https://openalex.org/W2465309725","https://openalex.org/W2466282755","https://openalex.org/W2467743264","https://openalex.org/W2473360228","https://openalex.org/W2473989358","https://openalex.org/W2800600342","https://openalex.org/W2805807001","https://openalex.org/W2963341956","https://openalex.org/W2963510222","https://openalex.org/W2963748441","https://openalex.org/W3035390927","https://openalex.org/W3133702157","https://openalex.org/W3163832451","https://openalex.org/W3169483174","https://openalex.org/W3170989320","https://openalex.org/W3183368628","https://openalex.org/W3183610699","https://openalex.org/W3184189983","https://openalex.org/W3184418820","https://openalex.org/W3185120251","https://openalex.org/W3185421637","https://openalex.org/W3185552631","https://openalex.org/W3211950664","https://openalex.org/W3212021444","https://openalex.org/W4206706211","https://openalex.org/W4229053887","https://openalex.org/W4292939171","https://openalex.org/W4378174351","https://openalex.org/W4385681388","https://openalex.org/W4386311574"],"related_works":["https://openalex.org/W4393232657","https://openalex.org/W4390638272","https://openalex.org/W2472237121","https://openalex.org/W4323316863","https://openalex.org/W1985111449","https://openalex.org/W4304789336","https://openalex.org/W2340692695","https://openalex.org/W4306175439","https://openalex.org/W2012556673","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"work,":[3],"we":[4,160],"present":[5],"a":[6,95,137,145,166,176],"novel":[7],"approach":[8,68],"to":[9,90],"lexical":[10],"complexity":[11],"prediction":[12],"(LCP)":[13],"that":[14,171,193],"combines":[15],"diverse":[16],"linguistic":[17,32,104,150,173],"features":[18,33,48,105,151,174],"with":[19,34,106,186],"encodings":[20,107],"from":[21,36,94,108],"deep":[22,110,187],"neural":[23],"networks.":[24],"We":[25,65],"explore":[26],"the":[27,122,129,156],"integration":[28],"of":[29,103,124,142,164],"23":[30],"handcrafted":[31,172],"embeddings":[35],"two":[37,70],"well-known":[38],"language":[39,85],"models:":[40],"BERT":[41],"and":[42,61,78,116],"XLM-RoBERTa.":[43],"Our":[44,98,190],"method":[45],"concatenates":[46],"these":[47],"before":[49],"inputting":[50],"them":[51],"into":[52],"various":[53],"machine":[54],"learning":[55,111,188],"algorithms,":[56],"including":[57],"SVM,":[58],"Random":[59],"Forest,":[60],"fine-tuned":[62],"transformer":[63],"models.":[64],"evaluate":[66],"our":[67,125,133],"using":[69,149],"datasets:":[71],"CompLex":[72,131],"for":[73,80,203],"English":[74,130],"(a":[75,82],"high-resource":[76],"language)":[77],"CLexIS2":[79,158],"Spanish":[81,157],"relatively":[83],"low-resource":[84],"in":[86,179,207],"),":[87],"allowing":[88],"us":[89],"study":[91],"performance":[92],"issues":[93],"cross-lingual":[96],"perspective.":[97],"experiments":[99],"involve":[100],"different":[101],"combinations":[102],"pretrained":[109],"models,":[112],"testing":[113],"both":[114],"token-based":[115],"sequence-related":[117],"encodings.":[118],"The":[119],"results":[120],"demonstrate":[121],"effectiveness":[123],"hybrid":[126,194],"approach.":[127],"For":[128],"corpus,":[132,159],"best":[134],"model":[135],"achieved":[136,161],"mean":[138],"absolute":[139],"error":[140],"(MAE)":[141],"0.0683,":[143],"representing":[144],"29.2%":[146],"improvement":[147],"over":[148,199],"alone":[152],"(MAE":[153],"0.0965).":[154],"On":[155],"an":[162],"MAE":[163],"0.1323,":[165],"19.4.":[167],"These":[168],"findings":[169],"show":[170],"play":[175],"fundamental":[177],"role":[178],"achieving":[180],"higher":[181],"performance,":[182],"particularly":[183],"when":[184],"combined":[185],"approaches.":[189],"work":[191],"suggests":[192],"approaches":[195],"should":[196],"be":[197],"considered":[198],"full":[200],"end-to-end":[201],"solutions":[202],"LCP":[204],"tasks,":[205],"especially":[206],"multilingual":[208],"contexts.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
