{"id":"https://openalex.org/W2100658491","doi":"https://doi.org/10.1145/1277741.1277782","title":"Multiple-signal duplicate detection for search evaluation","display_name":"Multiple-signal duplicate detection for search evaluation","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2100658491","doi":"https://doi.org/10.1145/1277741.1277782","mag":"2100658491"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual 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/A5048235002","display_name":"Scott B. Huffman","orcid":"https://orcid.org/0000-0002-4329-7049"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Scott Huffman","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047655514","display_name":"April Rasala Lehman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"April Lehman","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037776590","display_name":"Alexei P. Stolboushkin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexei Stolboushkin","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027948957","display_name":"Howard Wong-Toi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Wong-Toi","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045464812","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0003-2164-8175"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039468901","display_name":"Hein Roehrig","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hein Roehrig","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048235002"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.3467,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89915051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9976999759674072,"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":0.9976000189781189,"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":0.845906674861908},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.7489356994628906},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6828819513320923},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.658854067325592},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5686880946159363},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.559386670589447},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49741485714912415},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4246671199798584},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38183459639549255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2864651083946228},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1406954824924469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845906674861908},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.7489356994628906},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6828819513320923},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.658854067325592},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5686880946159363},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.559386670589447},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49741485714912415},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4246671199798584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38183459639549255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2864651083946228},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1406954824924469},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1277741.1277782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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":19,"referenced_works":["https://openalex.org/W1536700701","https://openalex.org/W1543320899","https://openalex.org/W1596691921","https://openalex.org/W1604437383","https://openalex.org/W1609518033","https://openalex.org/W1670263352","https://openalex.org/W1941707302","https://openalex.org/W1997657677","https://openalex.org/W2007842132","https://openalex.org/W2012833704","https://openalex.org/W2069870183","https://openalex.org/W2085922539","https://openalex.org/W2101867844","https://openalex.org/W2111295912","https://openalex.org/W2123504579","https://openalex.org/W2128859735","https://openalex.org/W2152565070","https://openalex.org/W6636190696","https://openalex.org/W6637074454"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"We":[0,156,210],"consider":[1],"the":[2,84,87,132,142,150,154,178,183,195,202,206,213],"problem":[3],"of":[4,18,57,89,106,131,135,149,153,216,222],"duplicate":[5,29,44,79,124],"document":[6],"detection":[7,45,80,125],"for":[8,21,43,83,103],"search":[9],"evaluation.":[10],"Given":[11],"a":[12,15,55,136,146],"query":[13],"and":[14,35,165,182],"small":[16],"number":[17,88],"web":[19,30,140],"results":[20,82],"that":[22,212,221],"query,":[23,86],"we":[24,74,95,188],"show":[25,211],"how":[26],"to":[27,98,117,161,180,185,208],"detect":[28],"documents":[31],"with":[32,54,78,111,119],"precision":[33,51,66,120,184],"~0.91":[34,52],"recall":[36,56,62,116,179,207],"~77.":[37],"In":[38,138],"contrast,":[39],"Charikar's":[40],"algorithm,":[41],"designed":[42],"in":[46,61,163],"an":[47],"indexing":[48],"pipeline,":[49],"achieves":[50],"but":[53],"~0.58.":[58],"Our":[59],"improvement":[60],"while":[63],"maintaining":[64],"high":[65],"comes":[67],"from":[68],"combining":[69],"three":[70],"ideas.":[71],"First,":[72],"because":[73],"are":[75],"only":[76],"concerned":[77],"among":[81],"same":[85],"pairwise":[90,101],"comparisons":[91],"is":[92,144],"small.":[93],"Therefore":[94],"can":[96],"afford":[97],"compute":[99],"multiple":[100],"signals":[102,170,192],"each":[104],"pair":[105],"documents.":[107],"A":[108],"model":[109,219],"learned":[110],"standard":[112],"machine-learning":[113],"techniques":[114,160],"improves":[115,177,205],"~0.68":[118],"~0.90.":[121],"Second,":[122],"most":[123],"has":[126],"focused":[127],"on":[128,172,194,201],"text":[129],"analysis":[130],"HTML":[133,143],"contents":[134,152],"document.":[137],"some":[139],"pages":[141],"not":[145],"good":[147],"indicator":[148],"final":[151,218],"page.":[155],"use":[157],"extended":[158],"fetching":[159],"fill":[162],"frames":[164],"execute":[166],"Java":[167],"script.":[168],"Including":[169],"based":[171,193,200],"our":[173],"richer":[174,203],"fetches":[175,204],"further":[176],"~0.75":[181],"~0.91.":[186],"Finally,":[187],"also":[189],"explore":[190],"using":[191],"query.":[196],"Comparing":[197],"contextual":[198],"snippets":[199],"~0.77.":[209],"overall":[214],"accuracy":[215],"this":[217],"approaches":[220],"human":[223],"judges.":[224]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}