{"id":"https://openalex.org/W2127994479","doi":"https://doi.org/10.1145/1099554.1099634","title":"Information retrieval and machine learning for probabilistic schema matching","display_name":"Information retrieval and machine learning for probabilistic schema matching","publication_year":2005,"publication_date":"2005-10-31","ids":{"openalex":"https://openalex.org/W2127994479","doi":"https://doi.org/10.1145/1099554.1099634","mag":"2127994479"},"language":"en","primary_location":{"id":"doi:10.1145/1099554.1099634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"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":"https://openalex.org/A5014421505","display_name":"Henrik Nottelmann","orcid":null},"institutions":[{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Henrik Nottelmann","raw_affiliation_strings":["University of Duisburg-Essen, Duisburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Duisburg-Essen, Duisburg, Germany","institution_ids":["https://openalex.org/I62318514"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021966059","display_name":"Umberto Straccia","orcid":"https://orcid.org/0000-0001-5998-6757"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Umberto Straccia","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy","ISTI--CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"ISTI--CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2465,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53842338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9997000098228455,"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/T11719","display_name":"Data Quality and Management","score":0.9962000250816345,"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":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.9138661623001099},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7955217361450195},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7833676338195801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7247356176376343},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5846158266067505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5347971320152283},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4354691505432129},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4203602373600006},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3614954948425293},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.22766682505607605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12694182991981506}],"concepts":[{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.9138661623001099},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7955217361450195},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7833676338195801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247356176376343},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5846158266067505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5347971320152283},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4354691505432129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4203602373600006},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3614954948425293},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.22766682505607605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12694182991981506},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1099554.1099634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:dnet:people______::cc67142f3b1fc05c5807ba2d142a57c1","is_oa":false,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::cc67142f3b1fc05c5807ba2d142a57c1","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"14th ACM Conference on Information and Knowledge Management (CIKM-05), pp. 295\u2013296, Bremen, November 2005","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1482882345","https://openalex.org/W1505139855","https://openalex.org/W1516892340","https://openalex.org/W1534565126","https://openalex.org/W1541434994","https://openalex.org/W1555156738","https://openalex.org/W1589374951","https://openalex.org/W1593317353","https://openalex.org/W1990890881","https://openalex.org/W1992673035","https://openalex.org/W2008896880","https://openalex.org/W2020228538","https://openalex.org/W2042389627","https://openalex.org/W2085544069","https://openalex.org/W2102729564","https://openalex.org/W2108267498","https://openalex.org/W2110686900","https://openalex.org/W2118020653","https://openalex.org/W2122604280","https://openalex.org/W2150365753","https://openalex.org/W2156543375","https://openalex.org/W2157060173"],"related_works":["https://openalex.org/W2471940468","https://openalex.org/W4226075635","https://openalex.org/W3130973930","https://openalex.org/W2047599596","https://openalex.org/W2372910313","https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2029826694","https://openalex.org/W2159303222"],"abstract_inverted_index":{"Schema":[0],"matching":[1,67],"is":[2,44],"the":[3,37,53,57,62],"problem":[4],"of":[5,52,56],"finding":[6],"correspondences":[7],"(mapping":[8],"rules,":[9],"e.g.":[10],"logical":[11],"formulae)":[12],"between":[13],"heterogeneous":[14],"schemas.":[15],"This":[16],"paper":[17],"presents":[18],"a":[19,49],"probabilistic":[20,50],"framework,":[21],"called":[22],"sPLMap,":[23],"for":[24],"automatically":[25],"learning":[26],"schema":[27],"mapping":[28],"rules.":[29],"Similar":[30],"to":[31,47,60],"LSD,":[32],"different":[33],"techniques,":[34],"mostly":[35],"from":[36],"IR":[38],"field,":[39],"are":[40],"combined.Our":[41],"approach,":[42],"however,":[43],"also":[45],"able":[46],"give":[48],"interpretation":[51],"prediction":[54],"weights":[55],"candidates,":[58],"and":[59],"select":[61],"rule":[63],"set":[64],"with":[65],"highest":[66],"probability.":[68]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}