{"id":"https://openalex.org/W1979954747","doi":"https://doi.org/10.1145/1321440.1321483","title":"Structure-based inference of xml similarity for fuzzy duplicate detection","display_name":"Structure-based inference of xml similarity for fuzzy duplicate detection","publication_year":2007,"publication_date":"2007-11-06","ids":{"openalex":"https://openalex.org/W1979954747","doi":"https://doi.org/10.1145/1321440.1321483","mag":"1979954747"},"language":"en","primary_location":{"id":"doi:10.1145/1321440.1321483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1321440.1321483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth ACM conference on Conference on information and knowledge management","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/A5057522519","display_name":"Lu\u00eds Leit\u00e3o","orcid":"https://orcid.org/0009-0003-7792-1844"},"institutions":[{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Lu\u00eds Leit\u00e3o","raw_affiliation_strings":["Instituto Superior T\u00e9cnico, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto Superior T\u00e9cnico, Lisbon, Portugal","institution_ids":["https://openalex.org/I4387152517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011911239","display_name":"P\u00e1vel Calado","orcid":"https://orcid.org/0000-0001-6478-229X"},"institutions":[{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"P\u00e1vel Calado","raw_affiliation_strings":["Instituto Superior T\u00e9cnico, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto Superior T\u00e9cnico, Lisbon, Portugal","institution_ids":["https://openalex.org/I4387152517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108379531","display_name":"Melanie Weis","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Melanie Weis","raw_affiliation_strings":["Hasso Plattner Institut, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057522519"],"corresponding_institution_ids":["https://openalex.org/I4387152517"],"apc_list":null,"apc_paid":null,"fwci":5.7055,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.95696761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"302"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9934999942779541,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9886999726295471,"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":0.8021671772003174},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6679208278656006},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5527526140213013},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.48023349046707153},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.4490092098712921},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44645464420318604},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.44151967763900757},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4274214506149292},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.410273015499115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2192797064781189}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021671772003174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6679208278656006},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5527526140213013},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.48023349046707153},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.4490092098712921},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44645464420318604},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.44151967763900757},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4274214506149292},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.410273015499115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2192797064781189},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1321440.1321483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1321440.1321483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth ACM conference on Conference on information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W54366487","https://openalex.org/W1536860849","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1610496399","https://openalex.org/W1689241477","https://openalex.org/W1845040079","https://openalex.org/W2009716188","https://openalex.org/W2019976352","https://openalex.org/W2024770506","https://openalex.org/W2044746110","https://openalex.org/W2046020929","https://openalex.org/W2052390074","https://openalex.org/W2064143200","https://openalex.org/W2065290081","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2087183379","https://openalex.org/W2099813268","https://openalex.org/W2102869387","https://openalex.org/W2112912553","https://openalex.org/W2121790392","https://openalex.org/W2129598390","https://openalex.org/W2154756203","https://openalex.org/W2154785834","https://openalex.org/W2159080219","https://openalex.org/W2164456230","https://openalex.org/W2170654002","https://openalex.org/W4238306122","https://openalex.org/W4244833938","https://openalex.org/W6602213441","https://openalex.org/W6636177537","https://openalex.org/W6663500203","https://openalex.org/W6669040500","https://openalex.org/W6676669657"],"related_works":["https://openalex.org/W2085384747","https://openalex.org/W2088166309","https://openalex.org/W1891216533","https://openalex.org/W4312133475","https://openalex.org/W4238976562","https://openalex.org/W2276587472","https://openalex.org/W2615795876","https://openalex.org/W2049612369","https://openalex.org/W2770872919","https://openalex.org/W2156296249"],"abstract_inverted_index":{"Fuzzy":[0],"duplicate":[1,55,84,97,110,126,183],"detection":[2,56,98,111,184],"aims":[3],"at":[4],"identifying":[5],"multiple":[6,47],"representations":[7],"of":[8,20,63,86,128,134,169],"real-world":[9],"objects":[10],"stored":[11,40],"in":[12,24,41,46,57,92,112],"a":[13,18,34,42,64,105,143,166,181],"data":[14,25,27,30,39,65,71,164],"source,":[15],"and":[16,114,157,171],"is":[17,151,176],"task":[19],"critical":[21],"practical":[22],"relevance":[23],"cleaning,":[26],"mining,":[28],"or":[29,69],"integration.":[31],"It":[32],"has":[33],"long":[35],"history":[36],"for":[37,53,108],"relational":[38],"single":[43],"table":[44],"(or":[45],"tables":[48],"with":[49,163],"equal":[50],"schema).":[51],"Algorithms":[52],"fuzzy":[54,109],"more":[58],"complex":[59],"structures,":[60],"e.g.,":[61,90],"hierarchies":[62],"warehouse,":[66],"XML":[67,116,189],"data,":[68,94],"graph":[70],"have":[72],"only":[73,123],"recently":[74],"emerged.":[75],"These":[76],"algorithms":[77],"use":[78],"similarity":[79],"measures":[80],"that":[81],"consider":[82],"the":[83,125,132,148],"status":[85,127],"their":[87],"direct":[88],"neighbors,":[89],"children":[91],"hierarchical":[93,113],"to":[95,153,179],"improve":[96],"effectiveness.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103],"propose":[104],"novel":[106],"method":[107],"semi-structured":[115],"data.":[117],"Unlike":[118],"previous":[119],"approaches,":[120],"it":[121],"not":[122],"considers":[124],"children,":[129],"but":[130],"rather":[131],"probability":[133],"descendants":[135],"being":[136],"duplicates.":[137],"Probabilities":[138],"are":[139],"computed":[140],"efficiently":[141],"using":[142],"Bayesian":[144],"network.":[145],"Experiments":[146],"show":[147],"proposed":[149],"algorithm":[150],"able":[152,178],"maintain":[154],"high":[155,167],"precision":[156],"recall":[158],"values,":[159],"even":[160],"when":[161],"dealing":[162],"containing":[165],"amount":[168],"errors":[170],"missing":[172],"information.":[173],"Our":[174],"proposal":[175],"also":[177],"outperform":[180],"state-of-the-art":[182],"system":[185],"on":[186],"three":[187],"different":[188],"databases.":[190]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}