{"id":"https://openalex.org/W2065290081","doi":"https://doi.org/10.1145/1066157.1066207","title":"DogmatiX tracks down duplicates in XML","display_name":"DogmatiX tracks down duplicates in XML","publication_year":2005,"publication_date":"2005-06-14","ids":{"openalex":"https://openalex.org/W2065290081","doi":"https://doi.org/10.1145/1066157.1066207","mag":"2065290081"},"language":"en","primary_location":{"id":"doi:10.1145/1066157.1066207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18452/9199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108379531","display_name":"Melanie Weis","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Melanie Weis","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","[Humboldt Universitat zu Berlin, Berlin, Germany]"],"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"[Humboldt Universitat zu Berlin, Berlin, Germany]","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","[Humboldt Universitat zu Berlin, Berlin, Germany]"],"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"[Humboldt Universitat zu Berlin, Berlin, Germany]","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108379531"],"corresponding_institution_ids":["https://openalex.org/I39343248"],"apc_list":null,"apc_paid":null,"fwci":13.5078,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.9911187,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"431","last_page":"442"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9968000054359436,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8260257244110107},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7906349897384644},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6141047477722168},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5363155007362366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5197595953941345},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.492735892534256},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.4581415355205536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1900484263896942},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08178955316543579},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.06449103355407715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260257244110107},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7906349897384644},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6141047477722168},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5363155007362366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5197595953941345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.492735892534256},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.4581415355205536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1900484263896942},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08178955316543579},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.06449103355407715},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1066157.1066207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.143","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.informatik.hu-berlin.de/mac/publications/SIGMOD05.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.hu-berlin.de:18452/9851","is_oa":false,"landing_page_url":"http://edoc.hu-berlin.de/18452/9851","pdf_url":null,"source":{"id":"https://openalex.org/S4306400923","display_name":"edoc Publication server (Humboldt University of Berlin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39343248","host_organization_name":"Humboldt-Universit\u00e4t zu Berlin","host_organization_lineage":["https://openalex.org/I39343248"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},{"id":"doi:10.18452/9199","is_oa":true,"landing_page_url":"https://doi.org/10.18452/9199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400923","display_name":"edoc Publication server (Humboldt University of Berlin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39343248","host_organization_name":"Humboldt-Universit\u00e4t zu Berlin","host_organization_lineage":["https://openalex.org/I39343248"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18452/9199","is_oa":true,"landing_page_url":"https://doi.org/10.18452/9199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400923","display_name":"edoc Publication server (Humboldt University of Berlin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39343248","host_organization_name":"Humboldt-Universit\u00e4t zu Berlin","host_organization_lineage":["https://openalex.org/I39343248"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5398132153","display_name":null,"funder_award_id":"DFG grant","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5406723937","display_name":null,"funder_award_id":"NA 432","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1610496399","https://openalex.org/W1660390307","https://openalex.org/W1875120328","https://openalex.org/W1969056935","https://openalex.org/W2024770506","https://openalex.org/W2064143200","https://openalex.org/W2067566391","https://openalex.org/W2106895292","https://openalex.org/W2112912553","https://openalex.org/W2128600649","https://openalex.org/W2154711808","https://openalex.org/W2164456230","https://openalex.org/W2164501930","https://openalex.org/W2188351697","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W2401723157","https://openalex.org/W2952904874","https://openalex.org/W324626582","https://openalex.org/W4389302559","https://openalex.org/W1690653314"],"abstract_inverted_index":{"Duplicate":[0],"detection":[1,26,85,100],"is":[2,31],"the":[3,14,22,58,118,145],"problem":[4,59],"of":[5,24,120,132,151],"detecting":[6],"different":[7],"entries":[8],"in":[9,21,27,37,80],"a":[10,51,139],"data":[11,41,113,147],"source":[12],"representing":[13],"same":[15],"real-world":[16],"entity.":[17],"While":[18],"research":[19],"abounds":[20],"realm":[23],"duplicate":[25,55,72,77,84,99],"relational":[28],"data,":[29],"there":[30],"yet":[32],"little":[33],"work":[34],"for":[35,54],"duplicates":[36],"other,":[38],"more":[39],"complex":[40],"models,":[42],"such":[43],"as":[44,136,138],"XML.":[45],"In":[46],"this":[47,93],"paper,":[48],"we":[49,95],"present":[50],"generalized":[52],"framework":[53],"detection,":[56],"dividing":[57],"into":[60],"three":[61],"components:":[62],"candidate":[63],"definition":[64,73],"defining":[65,74],"which":[66,103,131],"objects":[67],"are":[68,79],"to":[69,88,129,134],"be":[70],"compared,":[71],"when":[75],"two":[76],"candidates":[78],"fact":[81],"duplicates,":[82],"and":[83],"specifying":[86],"how":[87],"efficiently":[89],"find":[90],"those":[91],"duplicates.Using":[92],"framework,":[94],"propose":[96,127],"an":[97],"XML":[98,105,146],"method,":[101],"DogmatiX,":[102],"compares":[104],"elements":[106],"based":[107],"not":[108],"only":[109],"on":[110,117],"their":[111,121],"direct":[112],"values,":[114],"but":[115],"also":[116],"similarity":[119,140],"parents,":[122],"children,":[123],"structure,":[124],"etc.":[125],"We":[126],"heuristics":[128,156],"determine":[130],"these":[133],"choose,":[135],"well":[137],"measure":[141],"specifically":[142],"geared":[143],"towards":[144],"model.":[148],"An":[149],"evaluation":[150],"our":[152,158],"algorithm":[153],"using":[154],"several":[155],"validates":[157],"approach.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
