{"id":"https://openalex.org/W2066492106","doi":"https://doi.org/10.1145/2505515.2505722","title":"Efficient filtering and ranking schemes for finding inclusion dependencies on the web","display_name":"Efficient filtering and ranking schemes for finding inclusion dependencies on the web","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W2066492106","doi":"https://doi.org/10.1145/2505515.2505722","mag":"2066492106"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071533497","display_name":"Atsuyuki Morishima","orcid":"https://orcid.org/0000-0003-4606-9065"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuyuki Morishima","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan",", University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":", University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084701530","display_name":"Erika Yumiya","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erika Yumiya","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan",", University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":", University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016493447","display_name":"Masami Takahashi","orcid":"https://orcid.org/0000-0002-4152-8018"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Takahashi","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan",", University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":", University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103130913","display_name":"Shigeo Sugimoto","orcid":"https://orcid.org/0000-0002-5341-7016"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeo Sugimoto","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan",", University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":", University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064322519","display_name":"Hiroyuki Kitagawa","orcid":"https://orcid.org/0000-0002-2984-2258"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroyuki Kitagawa","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan",", University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":", University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.15033553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"763","last_page":"768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9915000200271606,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.989300012588501,"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":0.7567719221115112},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5645690560340881},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.525519847869873},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.5253060460090637},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.467169851064682},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45856937766075134},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.45646584033966064},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.4520459473133087},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.448615700006485},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44455111026763916},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.43649137020111084},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.4281180500984192},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.41105154156684875},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.263988733291626},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17512699961662292},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12908530235290527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12807610630989075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567719221115112},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5645690560340881},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.525519847869873},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.5253060460090637},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.467169851064682},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45856937766075134},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.45646584033966064},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.4520459473133087},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.448615700006485},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44455111026763916},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.43649137020111084},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.4281180500984192},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.41105154156684875},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.263988733291626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17512699961662292},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12908530235290527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12807610630989075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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":3,"locations":[{"id":"doi:10.1145/2505515.2505722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:tsukuba.repo.nii.ac.jp:00030365","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402076","display_name":"Terrestrial Environment Research Center (University of Tsukuba)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146399215","host_organization_name":"University of Tsukuba","host_organization_lineage":["https://openalex.org/I146399215"],"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":"","raw_type":""},{"id":"pmh:oai:tsukuba.repo.nii.ac.jp:00030365","is_oa":true,"landing_page_url":"http://hdl.handle.net/2241/121239","pdf_url":null,"source":{"id":"https://openalex.org/S4306402076","display_name":"Terrestrial Environment Research Center (University of Tsukuba)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146399215","host_organization_name":"University of Tsukuba","host_organization_lineage":["https://openalex.org/I146399215"],"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":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:tsukuba.repo.nii.ac.jp:00030365","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402076","display_name":"Terrestrial Environment Research Center (University of Tsukuba)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I146399215","host_organization_name":"University of Tsukuba","host_organization_lineage":["https://openalex.org/I146399215"],"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":"","raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7699999809265137,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W39905481","https://openalex.org/W1487773791","https://openalex.org/W1559019261","https://openalex.org/W2010454887","https://openalex.org/W2012833704","https://openalex.org/W2038926861","https://openalex.org/W2059009730","https://openalex.org/W2083110727","https://openalex.org/W2097184821","https://openalex.org/W2112129552","https://openalex.org/W2116790080","https://openalex.org/W2121516976","https://openalex.org/W2121630402","https://openalex.org/W2127675794","https://openalex.org/W2128056631","https://openalex.org/W2129465925","https://openalex.org/W2145349611","https://openalex.org/W2159186077","https://openalex.org/W2161163216","https://openalex.org/W2167260896","https://openalex.org/W2587845636"],"related_works":["https://openalex.org/W4254879869","https://openalex.org/W3022576529","https://openalex.org/W2628526247","https://openalex.org/W2596401011","https://openalex.org/W2913569734","https://openalex.org/W3127229356","https://openalex.org/W2000801317","https://openalex.org/W2294604808","https://openalex.org/W2702570413","https://openalex.org/W4379521144"],"abstract_inverted_index":{"Data":[0],"integrity":[1],"constraints":[2],"are":[3,46,56],"fundamental":[4],"in":[5,48,60,96,105,142],"various":[6],"applications,":[7],"such":[8,41,54],"as":[9,42],"data":[10,43,118],"management,":[11,45],"integration,":[12],"cleaning,":[13],"and":[14,52,76,122],"schema":[15],"extraction.":[16],"In":[17,62],"this":[18],"paper,":[19],"we":[20,65,84,133,161],"address":[21],"the":[22,29,49,79,97,114,120,124,156],"problem":[23,32],"of":[24,38,68,117,130,167],"finding":[25],"inclusion":[26,39,74,126,150],"dependencies":[27,55,75],"on":[28,119],"Web.":[30],"The":[31,100,152],"is":[33,103],"important":[34],"because":[35],"(1)":[36],"applications":[37],"dependencies,":[40],"quality":[44],"beneficial":[47],"Web":[50],"context,":[51],"(2)":[53],"not":[57],"explicitly":[58],"given":[59],"general.":[61],"our":[63],"approach,":[64],"enumerate":[66],"pairs":[67,158,168],"HTML/XML":[69],"elements":[70],"that":[71,106,160],"possibly":[72],"represent":[73],"then":[77],"rank":[78],"results":[80],"for":[81,169],"verification.":[82],"First,":[83],"propose":[85,134],"a":[86,135,140,164],"bit-based":[87],"signature":[88,101],"scheme":[89,102,137,154],"to":[90,111,138],"efficiently":[91],"select":[92],"candidates":[93],"(element":[94],"pairs)":[95],"enumeration":[98],"process.":[99],"unique":[104],"it":[107],"supports":[108],"Jaccard":[109],"containment":[110],"deal":[112],"with":[113],"incomplete":[115],"nature":[116],"Web,":[121],"preserves":[123],"semiorder":[125],"relationship":[127],"among":[128],"sets":[129],"words.":[131],"Second,":[132],"ranking":[136,153],"support":[139],"user":[141],"checking":[143],"whether":[144],"each":[145],"enumerated":[146,157],"pair":[147],"actually":[148],"suggests":[149],"dependencies.":[151],"sorts":[155],"so":[159],"can":[162],"examine":[163],"small":[165],"number":[166],"simultaneously":[170],"verifying":[171],"many":[172],"pairs.":[173]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}
