{"id":"https://openalex.org/W4389131242","doi":"https://doi.org/10.1007/s10994-023-06472-0","title":"Word embeddings for retrieving tabular data from research publications","display_name":"Word embeddings for retrieving tabular data from research publications","publication_year":2023,"publication_date":"2023-11-29","ids":{"openalex":"https://openalex.org/W4389131242","doi":"https://doi.org/10.1007/s10994-023-06472-0"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-023-06472-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06472-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06472-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","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/s10994-023-06472-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067840269","display_name":"Alberto Berenguer","orcid":"https://orcid.org/0000-0002-2867-8329"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Alberto Berenguer","raw_affiliation_strings":["Department of Software and Computing Systems, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690, San Vicente del Raspeig, Spain"],"raw_orcid":"https://orcid.org/0000-0002-2867-8329","affiliations":[{"raw_affiliation_string":"Department of Software and Computing Systems, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690, San Vicente del Raspeig, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015502433","display_name":"Jos\u00e9-Norberto Maz\u00f3n","orcid":"https://orcid.org/0000-0001-7924-0880"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose-Norberto Maz\u00f3n","raw_affiliation_strings":["Department of Software and Computing Systems, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690, San Vicente del Raspeig, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software and Computing Systems, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690, San Vicente del Raspeig, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014858583","display_name":"David Tom\u00e1s","orcid":"https://orcid.org/0000-0003-3287-9366"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Tom\u00e1s","raw_affiliation_strings":["Department of Software and Computing Systems, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690, San Vicente del Raspeig, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software and Computing Systems, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690, San Vicente del Raspeig, Spain","institution_ids":["https://openalex.org/I130194489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5067840269"],"corresponding_institution_ids":["https://openalex.org/I130194489"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.382,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82088095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"113","issue":"4","first_page":"2227","last_page":"2248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.835699737071991},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7260054349899292},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.659303605556488},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6512708067893982},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6180264949798584},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5600524544715881},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5558547973632812},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5080645084381104},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4310169517993927},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4156695306301117},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41086938977241516},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4025905132293701},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3916683793067932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3036491274833679},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16646742820739746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835699737071991},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7260054349899292},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.659303605556488},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6512708067893982},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6180264949798584},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5600524544715881},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5558547973632812},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5080645084381104},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4310169517993927},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4156695306301117},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41086938977241516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4025905132293701},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3916683793067932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3036491274833679},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16646742820739746},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-023-06472-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06472-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06472-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:rua.ua.es:10045/138859","is_oa":true,"landing_page_url":"http://hdl.handle.net/10045/138859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400416","display_name":"Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130194489","host_organization_name":"University of Alicante","host_organization_lineage":["https://openalex.org/I130194489"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10994-023-06472-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06472-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06472-0.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389131242.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1560851690","https://openalex.org/W1662133657","https://openalex.org/W1978394996","https://openalex.org/W2108223890","https://openalex.org/W2140116426","https://openalex.org/W2153579005","https://openalex.org/W2162020046","https://openalex.org/W2250539671","https://openalex.org/W2398606196","https://openalex.org/W2493916176","https://openalex.org/W2525778437","https://openalex.org/W2788550262","https://openalex.org/W2882319491","https://openalex.org/W2899286282","https://openalex.org/W2950668200","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963191264","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W2970771982","https://openalex.org/W3008881932","https://openalex.org/W3026889466","https://openalex.org/W3035140194","https://openalex.org/W3035231859","https://openalex.org/W3035324702","https://openalex.org/W3099839495","https://openalex.org/W3099965312","https://openalex.org/W3102264439","https://openalex.org/W3162752841","https://openalex.org/W3208454977","https://openalex.org/W3212464620","https://openalex.org/W4205997760","https://openalex.org/W4281643271","https://openalex.org/W4285212312","https://openalex.org/W4288086192","https://openalex.org/W4315705867","https://openalex.org/W4385571873","https://openalex.org/W6739901393","https://openalex.org/W6769430610"],"related_works":["https://openalex.org/W947140380","https://openalex.org/W4286432911","https://openalex.org/W2911655849","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W4287599800","https://openalex.org/W3101154008"],"abstract_inverted_index":{"Abstract":[0],"Scientists":[1],"face":[2],"challenges":[3],"when":[4,178],"finding":[5],"datasets":[6,26,84,135],"related":[7,117],"to":[8,13,55,80,118,125,132,158,190],"their":[9,70,141],"research":[10,25,94,120,142],"problems":[11],"due":[12],"the":[14,36,40,43,105,119,160,184,195],"limitations":[15],"of":[16,45,59,89,110,186],"current":[17],"dataset":[18],"search":[19,71],"engines.":[20],"Existing":[21],"tools":[22],"for":[23,130,193],"searching":[24],"rely":[27],"on":[28,69],"publication":[29,41],"content":[30],"or":[31],"metadata,":[32],"do":[33],"not":[34],"considering":[35],"data":[37,64],"contained":[38],"in":[39,42,66,139],"form":[44],"tables.":[46,166],"Moreover,":[47],"scientists":[48,131],"require":[49],"more":[50],"elaborate":[51],"inputs":[52],"and":[53,104,165],"functionalities":[54],"retrieve":[56,81],"different":[57,155],"parts":[58],"an":[60,98],"article,":[61],"such":[62],"as":[63,97],"presented":[65],"tables,":[67],"based":[68],"purposes.":[72],"Therefore,":[73],"this":[74,146],"paper":[75],"proposes":[76],"a":[77,93,101,108,127],"novel":[78],"approach":[79,123],"relevant":[82,111],"tabular":[83],"from":[85,100,113,154],"publications.":[86],"The":[87,167],"input":[88],"our":[90],"system":[91],"is":[92,107],"problem":[95],"stated":[96],"abstract":[99],"scientific":[102,181],"paper,":[103],"output":[106],"set":[109],"tables":[112],"publications":[114],"that":[115,136,170],"are":[116],"problem.":[121],"This":[122],"aims":[124],"provide":[126],"better":[128],"solution":[129],"find":[133],"useful":[134],"support":[137],"them":[138],"addressing":[140],"problems.":[143],"To":[144],"validate":[145],"approach,":[147],"experiments":[148],"were":[149],"conducted":[150],"using":[151],"word":[152],"embedding":[153],"language":[156],"models":[157,172],"calculate":[159],"semantic":[161],"similarity":[162],"between":[163],"abstracts":[164],"results":[168],"showed":[169],"contextual":[171],"significantly":[173],"outperformed":[174],"non-contextual":[175],"models,":[176],"especially":[177],"pre-trained":[179],"with":[180],"data.":[182],"Furthermore,":[183],"importance":[185],"context":[187],"was":[188],"found":[189],"be":[191],"crucial":[192],"improving":[194],"results.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
