{"id":"https://openalex.org/W4400910545","doi":"https://doi.org/10.1109/icde60146.2024.00269","title":"Mitigating Data Sparsity in Integrated Data through Text Conceptualization","display_name":"Mitigating Data Sparsity in Integrated Data through Text Conceptualization","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4400910545","doi":"https://doi.org/10.1109/icde60146.2024.00269"},"language":"en","primary_location":{"id":"doi:10.1109/icde60146.2024.00269","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icde60146.2024.00269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstreams/86dce49a-9815-4158-a58a-7c944edbf1fe/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020636788","display_name":"Md. Ataur Rahman","orcid":"https://orcid.org/0000-0002-9092-8771"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Md Ataur Rahman","raw_affiliation_strings":["Universitat Polit&#x00E8;cnica de Catalunya,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit&#x00E8;cnica de Catalunya,Barcelona,Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013379001","display_name":"Sergi Nadal","orcid":"https://orcid.org/0000-0002-8565-952X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergi Nadal","raw_affiliation_strings":["Universitat Polit&#x00E8;cnica de Catalunya,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit&#x00E8;cnica de Catalunya,Barcelona,Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025851055","display_name":"Oscar E Romero","orcid":"https://orcid.org/0000-0003-0209-3258"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Oscar Romero","raw_affiliation_strings":["Universitat Polit&#x00E8;cnica de Catalunya,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit&#x00E8;cnica de Catalunya,Barcelona,Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090860653","display_name":"Dimitris Sacharidis","orcid":"https://orcid.org/0000-0001-5022-1483"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dimitris Sacharidis","raw_affiliation_strings":["Universit&#x00E9; Libre de Bruxelles,Brussels,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; Libre de Bruxelles,Brussels,Belgium","institution_ids":["https://openalex.org/I132053463"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0217,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86540986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"41","issue":null,"first_page":"3490","last_page":"3504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9246000051498413,"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":0.9246000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/conceptualization","display_name":"Conceptualization","score":0.8732634782791138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6579218506813049},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4602929353713989},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4595330059528351},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35392677783966064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2591208815574646},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1399809718132019}],"concepts":[{"id":"https://openalex.org/C90734943","wikidata":"https://www.wikidata.org/wiki/Q17008777","display_name":"Conceptualization","level":2,"score":0.8732634782791138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579218506813049},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4602929353713989},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4595330059528351},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35392677783966064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2591208815574646},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1399809718132019}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde60146.2024.00269","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icde60146.2024.00269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/414440","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/414440","pdf_url":"https://upcommons.upc.edu/bitstreams/86dce49a-9815-4158-a58a-7c944edbf1fe/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/414440","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/414440","pdf_url":"https://upcommons.upc.edu/bitstreams/86dce49a-9815-4158-a58a-7c944edbf1fe/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1551405195","display_name":null,"funder_award_id":"PID2020-117191RB-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G1855990336","display_name":null,"funder_award_id":".13039/501100011033","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2660406951","display_name":null,"funder_award_id":"/ AEI/10","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G3444595235","display_name":null,"funder_award_id":"955895","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G425668148","display_name":null,"funder_award_id":".13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5400894464","display_name":null,"funder_award_id":"PID2020-117191RB-I00","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5421974903","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G5805502524","display_name":null,"funder_award_id":"PID2020","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400910545.pdf"},"referenced_works_count":123,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W1172683740","https://openalex.org/W1489417030","https://openalex.org/W1490960179","https://openalex.org/W1562624811","https://openalex.org/W1607035479","https://openalex.org/W1614298861","https://openalex.org/W1921077622","https://openalex.org/W1992479406","https://openalex.org/W1992673035","https://openalex.org/W1997458143","https://openalex.org/W2008639146","https://openalex.org/W2046298800","https://openalex.org/W2061848042","https://openalex.org/W2082055368","https://openalex.org/W2099964107","https://openalex.org/W2101553882","https://openalex.org/W2116434686","https://openalex.org/W2116781287","https://openalex.org/W2141456009","https://openalex.org/W2163107094","https://openalex.org/W2168041406","https://openalex.org/W2169099542","https://openalex.org/W2169491861","https://openalex.org/W2251913848","https://openalex.org/W2287926972","https://openalex.org/W2337288897","https://openalex.org/W2346452181","https://openalex.org/W2363785281","https://openalex.org/W2419271927","https://openalex.org/W2437617937","https://openalex.org/W2528773445","https://openalex.org/W2591700809","https://openalex.org/W2609602893","https://openalex.org/W2612649659","https://openalex.org/W2750779823","https://openalex.org/W2759211898","https://openalex.org/W2777063490","https://openalex.org/W2786447266","https://openalex.org/W2852434548","https://openalex.org/W2893303656","https://openalex.org/W2896457183","https://openalex.org/W2897852178","https://openalex.org/W2898256678","https://openalex.org/W2898795086","https://openalex.org/W2913389685","https://openalex.org/W2915977242","https://openalex.org/W2925863688","https://openalex.org/W2955443275","https://openalex.org/W2964179635","https://openalex.org/W2965373594","https://openalex.org/W2971258845","https://openalex.org/W2983641625","https://openalex.org/W2983787653","https://openalex.org/W2985532129","https://openalex.org/W3013778764","https://openalex.org/W3016734568","https://openalex.org/W3034856749","https://openalex.org/W3082197983","https://openalex.org/W3092806957","https://openalex.org/W3096861907","https://openalex.org/W3096910105","https://openalex.org/W3097665023","https://openalex.org/W3099949346","https://openalex.org/W3133665323","https://openalex.org/W3133702157","https://openalex.org/W3153566724","https://openalex.org/W3159924169","https://openalex.org/W3179164182","https://openalex.org/W3180107114","https://openalex.org/W3197847098","https://openalex.org/W3216565947","https://openalex.org/W3217771537","https://openalex.org/W4205807230","https://openalex.org/W4212774754","https://openalex.org/W4221160512","https://openalex.org/W4224239544","https://openalex.org/W4225513420","https://openalex.org/W4238846128","https://openalex.org/W4240301789","https://openalex.org/W4250812601","https://openalex.org/W4281728635","https://openalex.org/W4283318325","https://openalex.org/W4285537247","https://openalex.org/W4317767732","https://openalex.org/W4375959300","https://openalex.org/W4382317644","https://openalex.org/W4385270540","https://openalex.org/W4385567170","https://openalex.org/W4385573284","https://openalex.org/W4385681676","https://openalex.org/W4385755296","https://openalex.org/W4386128198","https://openalex.org/W4386232130","https://openalex.org/W4386471522","https://openalex.org/W4387526446","https://openalex.org/W4387848774","https://openalex.org/W4389519108","https://openalex.org/W4389523957","https://openalex.org/W4391840379","https://openalex.org/W4392681182","https://openalex.org/W6636510571","https://openalex.org/W6677895631","https://openalex.org/W6682007918","https://openalex.org/W6690716442","https://openalex.org/W6736599075","https://openalex.org/W6747248625","https://openalex.org/W6754576228","https://openalex.org/W6761260114","https://openalex.org/W6777788148","https://openalex.org/W6782482366","https://openalex.org/W6784025715","https://openalex.org/W6785563718","https://openalex.org/W6793779171","https://openalex.org/W6794442401","https://openalex.org/W6800672646","https://openalex.org/W6803457874","https://openalex.org/W6810575825","https://openalex.org/W6838781100","https://openalex.org/W6838865847","https://openalex.org/W6840777981","https://openalex.org/W6847529687","https://openalex.org/W6852105821"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4362575170","https://openalex.org/W1532772865","https://openalex.org/W2531253623","https://openalex.org/W2984230149","https://openalex.org/W2112095637","https://openalex.org/W2237121679","https://openalex.org/W4390616414","https://openalex.org/W2006867289"],"abstract_inverted_index":{"We":[0,13,36],"study":[1],"the":[2,15,30,33,60,67,76,81,96],"data":[3,7,62],"sparsity":[4],"problem":[5,16],"for":[6,69],"generated":[8],"from":[9,17],"an":[10],"integration":[11],"system.":[12],"approach":[14,85],"a":[18,39],"textual":[19],"information":[20],"extraction":[21],"perspective":[22],"and":[23,63,91],"propose":[24],"to":[25],"conceptualize":[26],"external":[27],"documents":[28],"using":[29],"concepts":[31],"in":[32,86],"integrated":[34,61],"schema.":[35],"present":[37],"THOR,":[38],"novel":[40],"system":[41],"that,":[42],"unlike":[43],"related":[44],"approaches,":[45],"neither":[46],"relies":[47],"on":[48,59,75],"complex":[49],"rules":[50],"nor":[51],"models":[52],"trained":[53],"with":[54],"large":[55],"annotated":[56],"corpus,":[57],"but":[58],"its":[64],"schema":[65],"without":[66],"need":[68],"human":[70],"annotations.":[71],"An":[72],"extensive":[73],"evaluation":[74],"text":[77],"conceptualization":[78],"task":[79],"demonstrates":[80],"superiority":[82],"of":[83,88,93],"our":[84],"terms":[87],"F1-score,":[89],"effort":[90],"use":[92],"resources":[94],"over":[95],"state-of-the-art":[97],"language":[98],"models.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
