{"id":"https://openalex.org/W2128894810","doi":"https://doi.org/10.1145/1277741.1277827","title":"Federated text retrieval from uncooperative overlapped collections","display_name":"Federated text retrieval from uncooperative overlapped collections","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2128894810","doi":"https://doi.org/10.1145/1277741.1277827","mag":"2128894810"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277827","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/A5088114671","display_name":"Milad Shokouhi","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Milad Shokouhi","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088114671"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":2.3562,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.89649199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"495","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9980000257492065,"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/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7999365329742432},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6761406064033508},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5572312474250793},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.43541592359542847},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4287464916706085},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3509221374988556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10810154676437378},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.07358428835868835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999365329742432},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6761406064033508},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5572312474250793},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.43541592359542847},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4287464916706085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3509221374988556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10810154676437378},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07358428835868835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1277741.1277827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277827","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.527.3497","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.527.3497","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/en-us/um/people/milads/shozob-sigir07.pdf","raw_type":"text"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/32013","is_oa":false,"landing_page_url":"http://hdl.handle.net/11343/32013","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W153030323","https://openalex.org/W1605873790","https://openalex.org/W1810577788","https://openalex.org/W1964653195","https://openalex.org/W1970173714","https://openalex.org/W1986828474","https://openalex.org/W1998674327","https://openalex.org/W2002682102","https://openalex.org/W2009018050","https://openalex.org/W2013905639","https://openalex.org/W2021986193","https://openalex.org/W2035127985","https://openalex.org/W2038526807","https://openalex.org/W2061973112","https://openalex.org/W2073788020","https://openalex.org/W2086253379","https://openalex.org/W2115701094","https://openalex.org/W2116341550","https://openalex.org/W2117626478","https://openalex.org/W2118295805","https://openalex.org/W2130270641","https://openalex.org/W2154438473","https://openalex.org/W2157485377","https://openalex.org/W2157530996","https://openalex.org/W2170205495","https://openalex.org/W2171547693","https://openalex.org/W4255459561","https://openalex.org/W6638231485"],"related_works":["https://openalex.org/W167737004","https://openalex.org/W1964038241","https://openalex.org/W2185038817","https://openalex.org/W2004064649","https://openalex.org/W2385957133","https://openalex.org/W3590553","https://openalex.org/W3141094475","https://openalex.org/W2390285850","https://openalex.org/W2550180686","https://openalex.org/W2131355632"],"abstract_inverted_index":{"In":[0],"federated":[1,81],"text":[2],"retrieval":[3],"systems,":[4],"the":[5,13,33,40,68,72,98,122,129,151],"query":[6],"is":[7,36],"sent":[8],"to":[9,32,62,84,88,120],"multiple":[10],"collections":[11,20,41,48,86,103,155],"at":[12],"same":[14],"time.":[15],"The":[16],"results":[17],"returned":[18],"by":[19,25],"are":[21,141],"gathered":[22],"and":[23,77],"ranked":[24],"a":[26,93],"central":[27],"broker":[28],"that":[29,39,118],"presents":[30],"them":[31],"user.":[34],"It":[35],"usually":[37],"assumed":[38],"have":[42],"little":[43],"overlap.":[44,156],"However,":[45],"in":[46,67,128,143],"practice":[47],"may":[49],"share":[50],"many":[51],"common":[52],"documents":[53,127],"as":[54],"either":[55],"exact":[56],"or":[57],"near":[58],"duplicates,":[59],"potentially":[60],"leading":[61],"high":[63],"numbers":[64],"of":[65,80,100,124,139],"duplicates":[66],"final":[69,130],"results.":[70,131],"Considering":[71],"natural":[73],"band":[74],"width":[75],"restrictions":[76],"efficiency":[78],"issues":[79],"search,":[82],"sendingqueries":[83],"redundant":[85],"leads":[87],"unnecessary":[89],"costs.":[90],"We":[91,132],"propose":[92,113],"novel":[94],"method":[95],"for":[96],"estimating":[97],"rate":[99],"over-lap":[101],"among":[102],"based":[104],"on":[105],"sampling.":[106],"Then,":[107],"using":[108],"theestimated":[109],"overlap":[110,140],"statistics,":[111],"we":[112],"two":[114],"collection":[115],"selection":[116],"methods":[117],"aim":[119],"maximize":[121],"number":[123],"unique":[125],"relevant":[126],"show":[133],"experimentally":[134],"that,":[135],"although":[136],"our":[137,145],"estimates":[138],"not":[142],"exact,":[144],"suggested":[146],"techniques":[147],"can":[148],"significantly":[149],"improve":[150],"search":[152],"effectiveness":[153],"when":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
