{"id":"https://openalex.org/W4312615758","doi":"https://doi.org/10.1007/978-3-031-20627-6_16","title":"HoloCleanX: A Multi-source Heterogeneous Data Cleaning Solution Based on Lakehouse","display_name":"HoloCleanX: A Multi-source Heterogeneous Data Cleaning Solution Based on Lakehouse","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312615758","doi":"https://doi.org/10.1007/978-3-031-20627-6_16"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-20627-6_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-20627-6_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qin Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Cui","raw_affiliation_strings":["Henan University, Kaifeng, 475004, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Henan University, Kaifeng, 475004, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045758048","display_name":"Wenkui Zheng","orcid":"https://orcid.org/0000-0002-6293-3418"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenkui Zheng","raw_affiliation_strings":["Henan University, Kaifeng, 475004, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Henan University, Kaifeng, 475004, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019645865","display_name":"Wei Hou","orcid":"https://orcid.org/0000-0002-1066-0710"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hou","raw_affiliation_strings":["Henan University, Kaifeng, 475004, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Henan University, Kaifeng, 475004, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069331173","display_name":"Ming Sheng","orcid":"https://orcid.org/0009-0002-8813-4558"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Sheng","raw_affiliation_strings":["BNRist, DCST, RIIT, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, DCST, RIIT, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812702","display_name":"Peng Ren","orcid":"https://orcid.org/0000-0003-3941-7842"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Ren","raw_affiliation_strings":["BNRist, DCST, RIIT, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, DCST, RIIT, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789304","display_name":"Wang Chang","orcid":"https://orcid.org/0000-0003-3263-3163"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Chang","raw_affiliation_strings":["Henan University, Kaifeng, 475004, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Henan University, Kaifeng, 475004, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341802","display_name":"Xiang\u2010Yang Li","orcid":"https://orcid.org/0000-0002-6070-6625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"XiangYang Li","raw_affiliation_strings":["Beijing SGITG-Accenture Information Technology Co., Ltd., Beijing, 100031, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing SGITG-Accenture Information Technology Co., Ltd., Beijing, 100031, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11719","display_name":"Data Quality and Management","score":0.9944999814033508,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9939000010490417,"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":0.8952467441558838},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6559898853302002},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5723768472671509},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.46470916271209717},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.44314736127853394},{"id":"https://openalex.org/keywords/interactivity","display_name":"Interactivity","score":0.41636669635772705},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38409534096717834},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3837231695652008},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38012662529945374},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.1803848147392273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.140062153339386},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1318933665752411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8952467441558838},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6559898853302002},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5723768472671509},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.46470916271209717},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.44314736127853394},{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.41636669635772705},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38409534096717834},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3837231695652008},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38012662529945374},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.1803848147392273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.140062153339386},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1318933665752411},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-20627-6_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-20627-6_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2591700809","https://openalex.org/W2904119005","https://openalex.org/W2913533634","https://openalex.org/W2929941791","https://openalex.org/W2946053001","https://openalex.org/W2948145720","https://openalex.org/W2969922685","https://openalex.org/W2979866729","https://openalex.org/W3013771327","https://openalex.org/W3036397942","https://openalex.org/W3082522758","https://openalex.org/W3089208551","https://openalex.org/W3092441108","https://openalex.org/W3092870704","https://openalex.org/W3105977086","https://openalex.org/W3114953877","https://openalex.org/W3132841128","https://openalex.org/W3134074583","https://openalex.org/W3159903840","https://openalex.org/W3201057676","https://openalex.org/W3216784379","https://openalex.org/W4223650310","https://openalex.org/W6637681330"],"related_works":["https://openalex.org/W2319020389","https://openalex.org/W1975913006","https://openalex.org/W2747851897","https://openalex.org/W4240086805","https://openalex.org/W1513662110","https://openalex.org/W2063506784","https://openalex.org/W2272707781","https://openalex.org/W2013411520","https://openalex.org/W2521348551","https://openalex.org/W2162688250"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
