{"id":"https://openalex.org/W4386298140","doi":"https://doi.org/10.1007/978-3-031-42941-5_23","title":"Thesaurus-Based Transformation: A Classification Method for\u00a0Real Dirty Data","display_name":"Thesaurus-Based Transformation: A Classification Method for\u00a0Real Dirty Data","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386298140","doi":"https://doi.org/10.1007/978-3-031-42941-5_23"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-42941-5_23","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-42941-5_23","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04161946/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085650478","display_name":"Maxime Perrot","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107416","display_name":"Roche (France)","ror":"https://ror.org/01mqmer16","country_code":"FR","type":"company","lineage":["https://openalex.org/I118019719","https://openalex.org/I4210107416"]},{"id":"https://openalex.org/I171246369","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et d'A\u00e9rotechnique","ror":"https://ror.org/04jx68594","country_code":"FR","type":"facility","lineage":["https://openalex.org/I171246369"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Maxime Perrot","raw_affiliation_strings":["Bimedia, Roche-sur-Yon, France","LIAS, ISAE-ENSMA, Chasseneuil, France"],"affiliations":[{"raw_affiliation_string":"Bimedia, Roche-sur-Yon, France","institution_ids":["https://openalex.org/I4210107416"]},{"raw_affiliation_string":"LIAS, ISAE-ENSMA, Chasseneuil, France","institution_ids":["https://openalex.org/I171246369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078698314","display_name":"Micka\u00ebl Baron","orcid":"https://orcid.org/0000-0002-3356-0835"},"institutions":[{"id":"https://openalex.org/I171246369","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et d'A\u00e9rotechnique","ror":"https://ror.org/04jx68594","country_code":"FR","type":"facility","lineage":["https://openalex.org/I171246369"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Micka\u00ebl Baron","raw_affiliation_strings":["LIAS, ISAE-ENSMA, Chasseneuil, France"],"affiliations":[{"raw_affiliation_string":"LIAS, ISAE-ENSMA, Chasseneuil, France","institution_ids":["https://openalex.org/I171246369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079247322","display_name":"Brice Chardin","orcid":null},"institutions":[{"id":"https://openalex.org/I171246369","display_name":"\u00c9cole Nationale Sup\u00e9rieure de M\u00e9canique et d'A\u00e9rotechnique","ror":"https://ror.org/04jx68594","country_code":"FR","type":"facility","lineage":["https://openalex.org/I171246369"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Brice Chardin","raw_affiliation_strings":["LIAS, ISAE-ENSMA, Chasseneuil, France"],"affiliations":[{"raw_affiliation_string":"LIAS, ISAE-ENSMA, Chasseneuil, France","institution_ids":["https://openalex.org/I171246369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101218389","display_name":"St\u00e9phane Jean","orcid":null},"institutions":[{"id":"https://openalex.org/I32881790","display_name":"Universit\u00e9 de Poitiers","ror":"https://ror.org/04xhy8q59","country_code":"FR","type":"education","lineage":["https://openalex.org/I32881790"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Jean","raw_affiliation_strings":["LIAS, Universit\u00e9 de Poitiers, Poitiers, France"],"affiliations":[{"raw_affiliation_string":"LIAS, Universit\u00e9 de Poitiers, Poitiers, France","institution_ids":["https://openalex.org/I32881790"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085650478"],"corresponding_institution_ids":["https://openalex.org/I171246369","https://openalex.org/I4210107416"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31959417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"256","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9958999752998352,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9915000200271606,"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/categorical-variable","display_name":"Categorical variable","score":0.805924117565155},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7523476481437683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7351078987121582},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.715043306350708},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5760042667388916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5564195513725281},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.518740713596344},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4940843880176544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580082595348358},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4315224289894104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42312490940093994},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3363129496574402},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32950571179389954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1251564621925354}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.805924117565155},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7523476481437683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351078987121582},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.715043306350708},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5760042667388916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5564195513725281},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.518740713596344},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4940843880176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580082595348358},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4315224289894104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42312490940093994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3363129496574402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32950571179389954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1251564621925354},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-031-42941-5_23","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-42941-5_23","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-04161946v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04161946","pdf_url":"https://hal.science/hal-04161946/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Advances in Databases and Information Systems (ADBIS), Sep 2023, Barcelona, Spain. pp.256-265, &#x27E8;10.1007/978-3-031-42941-5_23&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04161946v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04161946","pdf_url":"https://hal.science/hal-04161946/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Advances in Databases and Information Systems (ADBIS), Sep 2023, Barcelona, Spain. pp.256-265, &#x27E8;10.1007/978-3-031-42941-5_23&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386298140.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W1986966428","https://openalex.org/W2037332326","https://openalex.org/W2045821558","https://openalex.org/W2128728535","https://openalex.org/W2159495802","https://openalex.org/W2295598076","https://openalex.org/W2946417913","https://openalex.org/W2963105378","https://openalex.org/W3202428668"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W4386799044","https://openalex.org/W2101155126","https://openalex.org/W2773208253"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2025-10-10T00:00:00"}
