{"id":"https://openalex.org/W2110166424","doi":"https://doi.org/10.1145/1835449.1835520","title":"Adaptive near-duplicate detection via similarity learning","display_name":"Adaptive near-duplicate detection via similarity learning","publication_year":2010,"publication_date":"2010-07-19","ids":{"openalex":"https://openalex.org/W2110166424","doi":"https://doi.org/10.1145/1835449.1835520","mag":"2110166424"},"language":"en","primary_location":{"id":"doi:10.1145/1835449.1835520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","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/A5082305994","display_name":"Hannaneh Hajishirzi","orcid":"https://orcid.org/0000-0002-1055-6657"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hannaneh Hajishirzi","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066873932","display_name":"Wen-tau Yih","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-tau Yih","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111761879","display_name":"Aleksander Ko\u0142cz","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aleksander Kolcz","raw_affiliation_strings":["Microsoft, Redmond, WA, USA","Microsoft Redmond, WA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082305994"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":8.7277,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.98173339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"419","last_page":"426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976999759674072,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.9060556888580322},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.7661799192428589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7280055284500122},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.692168116569519},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6365119814872742},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6337968111038208},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.5291258096694946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5040873289108276},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.49953722953796387},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.448862224817276},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41559308767318726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3773033618927002},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.19996550679206848},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1207365095615387}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9060556888580322},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.7661799192428589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7280055284500122},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.692168116569519},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6365119814872742},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6337968111038208},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.5291258096694946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5040873289108276},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.49953722953796387},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.448862224817276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41559308767318726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3773033618927002},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.19996550679206848},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1207365095615387},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1835449.1835520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.5362","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.5362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/130851/ANDD.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3805906","https://openalex.org/W1502916507","https://openalex.org/W2004025009","https://openalex.org/W2012833704","https://openalex.org/W2038276547","https://openalex.org/W2067432306","https://openalex.org/W2081193615","https://openalex.org/W2085922539","https://openalex.org/W2109803107","https://openalex.org/W2119672021","https://openalex.org/W2139532006","https://openalex.org/W2143032627","https://openalex.org/W2145349611","https://openalex.org/W2147717514","https://openalex.org/W2148885851","https://openalex.org/W2152565070","https://openalex.org/W2153180170","https://openalex.org/W2154628803","https://openalex.org/W2164634022"],"related_works":["https://openalex.org/W4381948805","https://openalex.org/W4214483597","https://openalex.org/W4220978606","https://openalex.org/W2911483473","https://openalex.org/W4220894110","https://openalex.org/W4283738071","https://openalex.org/W4388145912","https://openalex.org/W3145472249","https://openalex.org/W4286850906","https://openalex.org/W4386612228"],"abstract_inverted_index":{"In":[0,63],"this":[1,59],"paper,":[2],"we":[3],"present":[4],"a":[5,17,26,39,71,130],"novel":[6],"near-duplicate":[7],"document":[8,24,77],"detection":[9],"method":[10,21,104],"that":[11],"can":[12,54,67],"easily":[13],"be":[14,55,68],"tuned":[15],"for":[16,38,85],"particular":[18],"domain.":[19],"Our":[20,103],"represents":[22],"each":[23],"as":[25,44,76,116],"real-valued":[27],"sparse":[28],"k-gram":[29],"vector,":[30],"where":[31],"the":[32,45,49,80,111,126],"weights":[33],"are":[34],"learned":[35],"to":[36,70],"optimize":[37],"specified":[40],"similarity":[41,47,61,87],"function,":[42],"such":[43,115],"cosine":[46],"or":[48],"Jaccard":[50],"coefficient.":[51],"Near-duplicate":[52],"documents":[53],"reliably":[56],"detected":[57],"through":[58,79],"improved":[60],"measure.":[62],"addition,":[64],"these":[65],"vectors":[66],"mapped":[69],"small":[72],"number":[73],"of":[74],"hash-values":[75],"signatures":[78],"locality":[81],"sensitive":[82],"hashing":[83],"scheme":[84],"efficient":[86],"computation.":[88],"We":[89],"demonstrate":[90],"our":[91],"approach":[92],"in":[93],"two":[94],"target":[95],"domains:":[96],"Web":[97],"news":[98],"articles":[99],"and":[100,118],"email":[101],"messages.":[102],"is":[105,129],"not":[106],"only":[107],"more":[108],"accurate":[109],"than":[110],"commonly":[112],"used":[113],"methods":[114],"Shingles":[117],"I-Match,":[119],"but":[120],"also":[121],"shows":[122],"consistent":[123],"improvement":[124],"across":[125],"domains,":[127],"which":[128],"desired":[131],"property":[132],"lacked":[133],"by":[134],"existing":[135],"methods.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}