{"id":"https://openalex.org/W1508790985","doi":"https://doi.org/10.1109/icde.2004.1320013","title":"A frequency-based approach for mining coverage statistics in data integration","display_name":"A frequency-based approach for mining coverage statistics in data integration","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W1508790985","doi":"https://doi.org/10.1109/icde.2004.1320013","mag":"1508790985"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2004.1320013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"},"type":"article","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/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zaiqing Nie","raw_affiliation_strings":["Department of Computer Science and Engineering, Arizona State University, Tempe, AZ, USA","Department of Computer Science & Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023323170","display_name":"Subbarao Kambhampati","orcid":"https://orcid.org/0000-0002-9069-0265"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subbarao Kambhampati","raw_affiliation_strings":["Department of Computer Science and Engineering, Arizona State University, Tempe, AZ, USA","Department of Computer Science & Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047496977"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":12.1121,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97966058,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"387","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7858405113220215},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5856638550758362},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5644828081130981},{"id":"https://openalex.org/keywords/summary-statistics","display_name":"Summary statistics","score":0.46307528018951416},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.32834959030151367},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3207423686981201},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10868087410926819}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858405113220215},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5856638550758362},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5644828081130981},{"id":"https://openalex.org/C32792767","wikidata":"https://www.wikidata.org/wiki/Q1370484","display_name":"Summary statistics","level":2,"score":0.46307528018951416},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32834959030151367},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3207423686981201},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10868087410926819},{"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":3,"locations":[{"id":"doi:10.1109/icde.2004.1320013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.8457","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rakaposhi.eas.asu.edu/freqbased.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.4254","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.4254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rakaposhi.eas.asu.edu/icde04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W82771818","https://openalex.org/W144900376","https://openalex.org/W1484413656","https://openalex.org/W1506285740","https://openalex.org/W1508790985","https://openalex.org/W1524520778","https://openalex.org/W1604794355","https://openalex.org/W1652673288","https://openalex.org/W1879587332","https://openalex.org/W2072001200","https://openalex.org/W2082493470","https://openalex.org/W2093480367","https://openalex.org/W2116908444","https://openalex.org/W2117218860","https://openalex.org/W2120780624","https://openalex.org/W2131006463","https://openalex.org/W2138944820","https://openalex.org/W2140190241","https://openalex.org/W2145543344","https://openalex.org/W2152022036","https://openalex.org/W2159552643","https://openalex.org/W2221553715","https://openalex.org/W6603471282","https://openalex.org/W6628750762","https://openalex.org/W6630476642","https://openalex.org/W6631407543","https://openalex.org/W6636453528","https://openalex.org/W6680704940","https://openalex.org/W7075341422"],"related_works":["https://openalex.org/W2046260256","https://openalex.org/W1969865489","https://openalex.org/W4313323870","https://openalex.org/W4240106746","https://openalex.org/W4230369419","https://openalex.org/W2991725409","https://openalex.org/W2010875215","https://openalex.org/W2954772049","https://openalex.org/W1971018524","https://openalex.org/W3214045955"],"abstract_inverted_index":{"Query":[0],"optimization":[1],"in":[2,91],"data":[3],"integration":[4],"requires":[5],"source":[6],"coverage":[7],"and":[8,12,59,75,82],"overlap":[9],"statistics.":[10],"Gathering":[11],"storing":[13],"the":[14,21,27,54,70,80,92],"required":[15],"statistics":[16,30,37,61],"presents":[17],"many":[18],"challenges,":[19],"not":[20],"least":[22],"of":[23,29,72,84,94],"which":[24,40],"is":[25],"controlling":[26],"amount":[28],"learned.":[31],"We":[32,68],"introduce":[33],"StatMiner,":[34],"a":[35,96],"novel":[36],"mining":[38],"approach":[39],"automatically":[41],"generates":[42],"attribute":[43,56],"value":[44,57],"hierarchies,":[45,58],"efficiently":[46],"discovers":[47],"frequently":[48],"accessed":[49],"query":[50],"classes":[51],"based":[52],"on":[53],"learned":[55],"learns":[60],"only":[62],"with":[63],"respect":[64],"to":[65],"these":[66],"classes.":[67],"describe":[69],"details":[71],"our":[73,85],"method,":[74],"present":[76],"experimental":[77],"results":[78],"demonstrating":[79],"efficiency":[81],"effectiveness":[83],"approach.":[86],"Our":[87],"experiments":[88],"are":[89],"done":[90],"context":[93],"BibFinder,":[95],"publicly":[97],"fielded":[98],"bibliography":[99],"mediator.":[100]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}