{"id":"https://openalex.org/W2064143200","doi":"https://doi.org/10.1145/1012453.1012456","title":"Detecting duplicate objects in XML documents","display_name":"Detecting duplicate objects in XML documents","publication_year":2004,"publication_date":"2004-06-18","ids":{"openalex":"https://openalex.org/W2064143200","doi":"https://doi.org/10.1145/1012453.1012456","mag":"2064143200"},"language":"en","primary_location":{"id":"doi:10.1145/1012453.1012456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1012453.1012456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 international workshop on Information quality in information systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18452/9221","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":9.586,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.9815111,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9825000166893005,"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":0.7608634233474731},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5192492008209229},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.4871232509613037},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3592517673969269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608634233474731},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5192492008209229},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.4871232509613037},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3592517673969269}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1012453.1012456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1012453.1012456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 international workshop on Information quality in information systems","raw_type":"proceedings-article"},{"id":"pmh:oai:edoc.hu-berlin.de:18452/9873","is_oa":false,"landing_page_url":"http://edoc.hu-berlin.de/18452/9873","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:10.18452/9221","is_oa":true,"landing_page_url":"https://doi.org/10.18452/9221","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:10.18452/9221","is_oa":true,"landing_page_url":"https://doi.org/10.18452/9221","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1484228408","https://openalex.org/W1485156179","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1604177764","https://openalex.org/W1610496399","https://openalex.org/W1875120328","https://openalex.org/W2001496424","https://openalex.org/W2024770506","https://openalex.org/W2067566391","https://openalex.org/W2106895292","https://openalex.org/W2112912553","https://openalex.org/W2128600649","https://openalex.org/W2150698190","https://openalex.org/W2154711808","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2169948249","https://openalex.org/W2912306800","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1788528807","https://openalex.org/W2361533086","https://openalex.org/W188567224","https://openalex.org/W2146043838","https://openalex.org/W1775720859","https://openalex.org/W2101966962","https://openalex.org/W2153015554","https://openalex.org/W2115485936","https://openalex.org/W2102585996","https://openalex.org/W7848518"],"abstract_inverted_index":{"The":[0,72,124],"problem":[1,37],"of":[2,78,91,114,132,148,153],"detecting":[3],"duplicate":[4,85,92],"entities":[5],"that":[6,64,163],"describe":[7],"the":[8,79,107,112,146],"same":[9],"real-world":[10],"object":[11],"(and":[12],"purging":[13],"them)":[14],"is":[15,122,135],"an":[16,69,118],"important":[17],"data":[18,24,27,45],"cleansing":[19],"task,":[20],"necessary":[21],"to":[22,35,48,83],"improve":[23],"quality.":[25],"For":[26],"stored":[28],"in":[29,51,68],"a":[30,61,75,97],"flat":[31],"relation,":[32],"numerous":[33],"solutions":[34],"this":[36,57],"exist.":[38],"As":[39],"XML":[40,53,70,80,167],"becomes":[41],"increasingly":[42],"popular":[43],"for":[44,130,151],"representation,":[46],"algorithms":[47],"detect":[49],"duplicates":[50,67,168],"nested":[52],"documents":[54],"are":[55,94,102],"required.In":[56],"paper,":[58],"we":[59,144],"present":[60],"domain-independent":[62],"algorithm":[63],"effectively":[65],"identifies":[66],"document.":[71],"solution":[73],"adopts":[74],"top-down":[76],"traversal":[77],"tree":[81],"structure":[82],"identify":[84],"elements":[86,93],"on":[87],"each":[88],"level.":[89],"Pairs":[90],"detected":[95],"using":[96,137,155],"thresholded":[98],"similarity":[99,125,129],"function,":[100],"and":[101,170],"then":[103],"clustered":[104],"by":[105],"computing":[106],"transitive":[108],"closure.":[109],"To":[110,141],"minimize":[111],"number":[113],"pairwise":[115],"element":[116],"comparisons,":[117],"appropriate":[119],"filter":[120],"function":[121],"used.":[123],"measure":[126],"involves":[127],"string":[128],"pairs":[131,152],"strings,":[133],"which":[134],"measured":[136],"their":[138],"edit":[139,149],"distance.":[140],"increase":[142],"efficiency,":[143],"avoid":[145],"computation":[147],"distance":[150],"strings":[154],"three":[156],"filtering":[157],"methods":[158],"subsequently.":[159],"First":[160],"experiments":[161],"show":[162],"our":[164],"approach":[165],"detects":[166],"accurately":[169],"efficiently.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
