{"id":"https://openalex.org/W2782832832","doi":"https://doi.org/10.1109/bigdata.2017.8258015","title":"Data context informed data wrangling","display_name":"Data context informed data wrangling","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2782832832","doi":"https://doi.org/10.1109/bigdata.2017.8258015","mag":"2782832832"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.manchester.ac.uk/en/publications/c6349bb1-3fbd-43bf-b85b-80772fb1396f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032869679","display_name":"Martin Koehler","orcid":"https://orcid.org/0000-0003-0377-9008"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martin Koehler","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004951878","display_name":"Alex Bogatu","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Bogatu","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020613765","display_name":"Cristina Civili","orcid":"https://orcid.org/0000-0002-4357-3509"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cristina Civili","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010193726","display_name":"\u039d\u03b9\u03ba\u03cc\u03bb\u03b1\u03bf\u03c2 \u039a\u03c9\u03bd\u03c3\u03c4\u03b1\u03bd\u03c4\u03af\u03bd\u03bf\u03c5","orcid":"https://orcid.org/0000-0003-3742-9276"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikolaos Konstantinou","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070591199","display_name":"E. W. Abel","orcid":"https://orcid.org/0000-0002-3694-5116"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edward Abel","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057541402","display_name":"Alvaro A. A. Fernandes","orcid":"https://orcid.org/0000-0002-6100-7199"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alvaro A. A. Fernandes","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105350782","display_name":"John Keane","orcid":"https://orcid.org/0000-0001-9022-4339"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Keane","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069883356","display_name":"Leonid Libkin","orcid":"https://orcid.org/0000-0002-6698-2735"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leonid Libkin","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066619159","display_name":"Norman W. Paton","orcid":"https://orcid.org/0000-0003-2008-6617"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Norman W. Paton","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5032869679"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":2.6944,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90805401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"956","last_page":"963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9973999857902527,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9889000058174133,"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":0.7874578237533569},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6216088533401489},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5896600484848022},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.5871922373771667},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49522581696510315},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4742492735385895},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.4704251289367676},{"id":"https://openalex.org/keywords/data-verification","display_name":"Data verification","score":0.46283483505249023},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4409116506576538},{"id":"https://openalex.org/keywords/data-validation","display_name":"Data validation","score":0.4264102280139923},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42020827531814575},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.34196096658706665},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28262120485305786},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.2401866912841797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.23393666744232178},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12136384844779968},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08432522416114807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07799631357192993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874578237533569},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6216088533401489},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5896600484848022},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.5871922373771667},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49522581696510315},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4742492735385895},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4704251289367676},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.46283483505249023},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4409116506576538},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.4264102280139923},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42020827531814575},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34196096658706665},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28262120485305786},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2401866912841797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.23393666744232178},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12136384844779968},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08432522416114807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07799631357192993},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/bigdata.2017.8258015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/c6349bb1-3fbd-43bf-b85b-80772fb1396f","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/c6349bb1-3fbd-43bf-b85b-80772fb1396f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Koehler, M, Bogatu, A, Civili, C, Konstantinou, N, Abel, E, Fernandes, A, Keane, J, Libkin, L & Paton, N 2018, Data Context Informed Data Wrangling. in 2017 IEEE International Conference on Big Data (Big Data). IEEE, pp. 956-963, 2017 IEEE International Conference on Big Data (Big Data), Boston, Massachusetts, United States, 11/12/17. https://doi.org/10.1109/BigData.2017.8258015","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1811.09248","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.09248","pdf_url":"https://arxiv.org/pdf/1811.09248","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/c6349bb1-3fbd-43bf-b85b-80772fb1396f","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85047767183&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/6abb10e6-7fb1-4edd-81a7-bafdbcb2bda1","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6abb10e6-7fb1-4edd-81a7-bafdbcb2bda1","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"Koehler, M, Bogatu, A, Civili, C, Konstantinou, N, Abel, E, Fernandes, A A A, Keane, J, Libkin, L & Paton, N W 2018, Data context informed data wrangling. in 2017 IEEE International Conference on Big Data. Institute of Electrical and Electronics Engineers, 2017 IEEE International Conference on Big Data, Boston, United States, 11/12/17. https://doi.org/10.1109/BigData.2017.8258015","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/6abb10e6-7fb1-4edd-81a7-bafdbcb2bda1","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/6abb10e6-7fb1-4edd-81a7-bafdbcb2bda1","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/c6349bb1-3fbd-43bf-b85b-80772fb1396f","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/c6349bb1-3fbd-43bf-b85b-80772fb1396f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Koehler, M, Bogatu, A, Civili, C, Konstantinou, N, Abel, E, Fernandes, A, Keane, J, Libkin, L & Paton, N 2018, Data Context Informed Data Wrangling. in 2017 IEEE International Conference on Big Data (Big Data). IEEE, pp. 956-963, 2017 IEEE International Conference on Big Data (Big Data), Boston, Massachusetts, United States, 11/12/17. https://doi.org/10.1109/BigData.2017.8258015","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8400180575","display_name":null,"funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1556076816","https://openalex.org/W1965492961","https://openalex.org/W1998982581","https://openalex.org/W2063705591","https://openalex.org/W2083755493","https://openalex.org/W2113607096","https://openalex.org/W2114541504","https://openalex.org/W2132525863","https://openalex.org/W2137775416","https://openalex.org/W2140523882","https://openalex.org/W2143677795","https://openalex.org/W2161163216","https://openalex.org/W2293618136","https://openalex.org/W2296164608","https://openalex.org/W2315227351","https://openalex.org/W2427822648","https://openalex.org/W2439326083","https://openalex.org/W2493970676","https://openalex.org/W2544486974","https://openalex.org/W2584580687","https://openalex.org/W2584721087","https://openalex.org/W2612069656","https://openalex.org/W2612924628","https://openalex.org/W2626926457","https://openalex.org/W3000214033","https://openalex.org/W4237014379","https://openalex.org/W4237412827","https://openalex.org/W6633446409","https://openalex.org/W6680599078","https://openalex.org/W6680607918","https://openalex.org/W6723501177","https://openalex.org/W6732710093"],"related_works":["https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2029826694","https://openalex.org/W246914734","https://openalex.org/W2537291169","https://openalex.org/W2159303222","https://openalex.org/W2976128099","https://openalex.org/W1544437759","https://openalex.org/W1601291651"],"abstract_inverted_index":{"The":[0,131],"process":[1,30,80],"of":[2,48,87,96,145],"preparing":[3],"potentially":[4,92],"large":[5],"and":[6,128],"complex":[7],"data":[8,19,51,58,78,82,95,106,129,138],"sets":[9],"for":[10],"further":[11],"analysis":[12],"or":[13,45],"manual":[14,40],"examination":[15],"is":[16,133],"often":[17],"called":[18],"wrangling.":[20,147],"In":[21,66],"classical":[22],"warehousing":[23],"environments,":[24],"the":[25,109,118,143],"steps":[26,60,116],"in":[27,42,114,142],"such":[28],"a":[29,71,88],"have":[31],"been":[32],"carried":[33],"out":[34],"using":[35],"Extract-Transform-Load":[36],"platforms,":[37],"with":[38,91,105,135],"significant":[39],"involvement":[41],"specifying,":[43],"configuring":[44],"tuning":[46],"many":[47],"them.":[49],"Cost-effective":[50],"wrangling":[52,59,79,119],"processes":[53],"need":[54],"to":[55,73,111],"ensure":[56],"that":[57,98],"benefit":[61],"from":[62],"automation":[63,113],"wherever":[64],"possible.":[65],"this":[67],"paper,":[68],"we":[69],"define":[70],"methodology":[72],"fully":[74],"automate":[75],"an":[76],"end-to-end":[77],"incorporating":[81],"context,":[83],"which":[84],"associates":[85],"portions":[86],"target":[89],"schema":[90],"spurious":[93],"extensional":[94],"types":[97],"are":[99],"commonly":[100],"available.":[101],"Instance-based":[102],"evidence":[103],"together":[104],"profiling":[107],"paves":[108],"way":[110],"inform":[112],"several":[115],"within":[117],"process,":[120],"specifically,":[121],"matching,":[122],"mapping":[123],"validation,":[124],"value":[125],"format":[126],"transformation,":[127],"repair.":[130],"approach":[132],"evaluated":[134],"real":[136],"estate":[137],"showing":[139],"substantial":[140],"improvements":[141],"results":[144],"automated":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}
