{"id":"https://openalex.org/W4310398100","doi":"https://doi.org/10.1007/s00521-022-08066-8","title":"Contextual word embeddings for tabular data search and integration","display_name":"Contextual word embeddings for tabular data search and integration","publication_year":2022,"publication_date":"2022-11-30","ids":{"openalex":"https://openalex.org/W4310398100","doi":"https://doi.org/10.1007/s00521-022-08066-8"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-022-08066-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-08066-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-08066-8.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/s00521-022-08066-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066901043","display_name":"Jos\u00e9 Pilaluisa","orcid":null},"institutions":[{"id":"https://openalex.org/I141930428","display_name":"Central University of Ecuador","ror":"https://ror.org/010n0x685","country_code":"EC","type":"education","lineage":["https://openalex.org/I141930428"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Pilaluisa","raw_affiliation_strings":["Faculty of Engineering, Physical Sciences and Mathematics, Central University of Ecuador, Avenida Universitaria, 170129, Quito, Ecuador"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Physical Sciences and Mathematics, Central University of Ecuador, Avenida Universitaria, 170129, Quito, Ecuador","institution_ids":["https://openalex.org/I141930428"]}]},{"author_position":"middle","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":true,"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"],"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/A5028127124","display_name":"Borja Navarro-Colorado","orcid":"https://orcid.org/0000-0002-7709-547X"},"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":"Borja Navarro-Colorado","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"],"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/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"],"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":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014858583"],"corresponding_institution_ids":["https://openalex.org/I130194489"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.5075,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69405419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"35","issue":"13","first_page":"9319","last_page":"9333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.9943000078201294,"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":0.8558269739151001},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6055188775062561},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5575519800186157},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.547355592250824},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5182895064353943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4757920503616333},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46747469902038574},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4630001187324524},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.45275023579597473},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4513033628463745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43887633085250854},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4230566918849945},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3493519425392151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558269739151001},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6055188775062561},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5575519800186157},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.547355592250824},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5182895064353943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4757920503616333},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46747469902038574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4630001187324524},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45275023579597473},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4513033628463745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43887633085250854},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4230566918849945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3493519425392151},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00521-022-08066-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-08066-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-08066-8.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"},{"id":"pmh:oai:rua.ua.es:10045/130001","is_oa":true,"landing_page_url":"http://hdl.handle.net/10045/130001","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/s00521-022-08066-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-08066-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-08066-8.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":[],"awards":[{"id":"https://openalex.org/G2861334199","display_name":null,"funder_award_id":"GVA-COVID19/2021/103","funder_id":"https://openalex.org/F4320336489","funder_display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana"}],"funders":[{"id":"https://openalex.org/F4320311011","display_name":"Universidad de Alicante","ror":"https://ror.org/05t8bcz72"},{"id":"https://openalex.org/F4320336489","display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4310398100.pdf","grobid_xml":"https://content.openalex.org/works/W4310398100.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1576228976","https://openalex.org/W1969621019","https://openalex.org/W2046325278","https://openalex.org/W2108223890","https://openalex.org/W2162020046","https://openalex.org/W2188138540","https://openalex.org/W2250539671","https://openalex.org/W2292351001","https://openalex.org/W2398606196","https://openalex.org/W2740592503","https://openalex.org/W2788550262","https://openalex.org/W2798664493","https://openalex.org/W2888329843","https://openalex.org/W2889003264","https://openalex.org/W2899286282","https://openalex.org/W2913087274","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2998914929","https://openalex.org/W3007024586","https://openalex.org/W3007429250","https://openalex.org/W3008881932","https://openalex.org/W3026889466","https://openalex.org/W3034944976","https://openalex.org/W3035140194","https://openalex.org/W3035231859","https://openalex.org/W3099839495","https://openalex.org/W3099965312","https://openalex.org/W3102264439","https://openalex.org/W3162752841","https://openalex.org/W4205997760","https://openalex.org/W6601211009"],"related_works":["https://openalex.org/W2997512100","https://openalex.org/W2020540721","https://openalex.org/W2578916128","https://openalex.org/W1539050421","https://openalex.org/W2015950787","https://openalex.org/W3024381485","https://openalex.org/W4295267149","https://openalex.org/W1563147278","https://openalex.org/W2735335964","https://openalex.org/W2624106077"],"abstract_inverted_index":{"Abstract":[0],"This":[1,59],"paper":[2],"presents":[3],"a":[4,33,140],"new":[5],"approach":[6],"to":[7,65,164],"retrieve":[8],"and":[9,17,21,47,77,102,113,121,139],"further":[10],"integrate":[11],"tabular":[12,104],"datasets":[13],"(collections":[14],"of":[15,52,74,93],"rows":[16],"columns)":[18],"using":[19,32],"union":[20,161],"join":[22,88],"operations.":[23],"In":[24,149],"this":[25],"work,":[26],"both":[27,100],"processes":[28],"were":[29,116],"carried":[30,97],"out":[31,98],"similarity":[34],"measure":[35],"based":[36,55],"on":[37,56,99,124,160],"contextual":[38,67,119,133,154],"word":[39,68],"embeddings,":[40],"which":[41],"allows":[42],"finding":[43],"semantically":[44],"similar":[45],"tables":[46],"overcome":[48],"the":[49,62,71,81,87,150,158],"recall":[50],"problem":[51],"lexical":[53],"approaches":[54],"string":[57],"similarity.":[58],"work":[60],"is":[61],"first":[63,82],"attempt":[64],"use":[66,85],"embeddings":[69],"in":[70,86,144],"whole":[72],"pipeline":[73],"table":[75,147],"search":[76],"integration,":[78],"including":[79],"for":[80],"time":[83],"their":[84,94,122],"operation.":[89],"A":[90],"comprehensive":[91],"analysis":[92],"performance":[95],"was":[96,127],"retrieving":[101],"integrating":[103],"datasets,":[105],"comparing":[106],"them":[107],"with":[108],"context-free":[109,137,165],"models.":[110],"Column":[111],"headings":[112],"cell":[114],"values":[115],"used":[117],"as":[118],"information":[120],"impact":[123],"each":[125],"task":[126],"evaluated.":[128],"The":[129],"results":[130,159],"revealed":[131],"that":[132],"models":[134,138,155],"significantly":[135],"outperform":[136],"traditional":[141],"weighting":[142],"schema":[143],"ad":[145],"hoc":[146],"retrieval.":[148],"data":[151],"integration":[152],"task,":[153],"also":[156],"improved":[157],"operation":[162],"compared":[163],"approaches.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
