{"id":"https://openalex.org/W2115939989","doi":"https://doi.org/10.1145/2484028.2484033","title":"Taily","display_name":"Taily","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2115939989","doi":"https://doi.org/10.1145/2484028.2484033","mag":"2115939989"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th 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/A5088100009","display_name":"Robin Aly","orcid":"https://orcid.org/0000-0002-6787-0911"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Robin Aly","raw_affiliation_strings":["University Twente, Enschede, Netherlands"],"affiliations":[{"raw_affiliation_string":"University Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108167267","display_name":"Djoerd Hiemstra","orcid":"https://orcid.org/0000-0003-4967-2900"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Djoerd Hiemstra","raw_affiliation_strings":["University Twente, Enschede, Netherlands"],"affiliations":[{"raw_affiliation_string":"University Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075509168","display_name":"Thomas Demeester","orcid":"https://orcid.org/0000-0002-9901-5768"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thomas Demeester","raw_affiliation_strings":["Ghent University, Ghent, Belgium","[Ghent University, Ghent, BeLgium]"],"affiliations":[{"raw_affiliation_string":"Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I2801227569"]},{"raw_affiliation_string":"[Ghent University, Ghent, BeLgium]","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088100009"],"corresponding_institution_ids":["https://openalex.org/I94624287"],"apc_list":null,"apc_paid":null,"fwci":16.7114,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.98843603,"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":"673","last_page":"682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9972000122070312,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9947999715805054,"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":0.7067957520484924},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5760706663131714},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5314218997955322},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.511375367641449},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4525411128997803},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42231130599975586},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4041227400302887},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32453808188438416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25824618339538574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067957520484924},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5760706663131714},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5314218997955322},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.511375367641449},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4525411128997803},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42231130599975586},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4041227400302887},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32453808188438416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25824618339538574},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2484028.2484033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/a81244c3-1623-43de-88ce-adc60f619979","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/a81244c3-1623-43de-88ce-adc60f619979","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Aly, R, Hiemstra, D & Demeester, T 2013, Taily: shard selection using the tail of score distributions. in Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013. Association for Computing Machinery, New York, pp. 673-682, 36th Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2013, Dublin, Ireland, 29/07/13. https://doi.org/10.1145/2484028.2484033","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/227029","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/227029","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jones, G.J.F. (ed.), SIGIR'13: The Proceedings of the 36th International ACM SIGIR Conference on Research &amp; Development in Information Retrieval, July 28\u2013August 1, 2013 Dublin, Ireland, pp. 673-682","raw_type":"Article in monograph or in proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4577656949","display_name":null,"funder_award_id":"639.022.809","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G486964816","display_name":null,"funder_award_id":"project 6","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321015","display_name":"University of Twente","ror":"https://ror.org/006hf6230"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320322274","display_name":"iMinds","ror":"https://ror.org/03baec336"},{"id":"https://openalex.org/F4320322603","display_name":"Universiteit Gent","ror":"https://ror.org/00cv9y106"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2808882","https://openalex.org/W1564059483","https://openalex.org/W1685426458","https://openalex.org/W1982371998","https://openalex.org/W1990388042","https://openalex.org/W1995819710","https://openalex.org/W1998481788","https://openalex.org/W2001664274","https://openalex.org/W2002682102","https://openalex.org/W2005066702","https://openalex.org/W2036295879","https://openalex.org/W2070740689","https://openalex.org/W2086253379","https://openalex.org/W2098294664","https://openalex.org/W2099435855","https://openalex.org/W2104588805","https://openalex.org/W2105293186","https://openalex.org/W2108871129","https://openalex.org/W2112668678","https://openalex.org/W2121928206","https://openalex.org/W2147028271","https://openalex.org/W2171144050","https://openalex.org/W2340309946","https://openalex.org/W4255459561","https://openalex.org/W6600104628","https://openalex.org/W6674864166"],"related_works":["https://openalex.org/W2980611886","https://openalex.org/W42295635","https://openalex.org/W1973996291","https://openalex.org/W2330575325","https://openalex.org/W2163803519","https://openalex.org/W2497592525","https://openalex.org/W3096145648","https://openalex.org/W3197510923","https://openalex.org/W4205762803","https://openalex.org/W2370579019"],"abstract_inverted_index":{"Search":[0],"engines":[1],"can":[2],"improve":[3],"their":[4,28,157],"efficiency":[5,158],"by":[6,159],"selecting":[7],"only":[8],"few":[9],"promising":[10],"shards":[11,85],"for":[12],"each":[13,77],"query.":[14],"State-of-the-art":[15],"shard":[16,67,78],"selection":[17,68],"algorithms":[18],"first":[19],"query":[20],"a":[21,65,72,80],"central":[22,41],"index":[23,42],"of":[24,52,93,100,109,126,164],"sampled":[25,59],"documents,":[26],"and":[27,83,107,117,132,143,154,167],"effectiveness":[29,51,150],"is":[30,130],"similar":[31,149],"to":[32,151],"searching":[33],"all":[34],"shards.":[35,118],"However,":[36],"the":[37,40,50,58,91,94,98,105,110,115],"search":[38],"in":[39,76,90,114,162],"also":[43],"hurts":[44],"efficiency.":[45],"Additionally,":[46],"we":[47],"show":[48,145],"that":[49,70,146],"these":[53],"approaches":[54],"varies":[55],"substantially":[56],"with":[57,86],"documents.":[60],"This":[61],"paper":[62],"proposes":[63],"Taily,":[64],"novel":[66],"algorithm":[69],"models":[71],"query's":[73],"score":[74,101,111],"distribution":[75,82],"as":[79],"Gamma":[81],"selects":[84],"highly":[87],"scored":[88],"documents":[89],"tail":[92],"distribution.":[95],"Taily":[96,120,147],"estimates":[97],"parameters":[99],"distributions":[102],"based":[103],"on":[104,122,137],"mean":[106],"variance":[108],"function's":[112],"features":[113],"collections":[116,140],"Because":[119],"operates":[121],"term":[123],"statistics":[124],"instead":[125],"document":[127],"samples,":[128],"it":[129],"efficient":[131],"has":[133],"deterministic":[134],"effectiveness.":[135],"Experiments":[136],"large":[138],"web":[139],"(Gov2,":[141],"CluewebA":[142],"CluewebB)":[144],"achieves":[148],"sample-based":[152],"approaches,":[153],"improves":[155],"upon":[156],"roughly":[160],"20%":[161],"terms":[163],"used":[165],"resources":[166],"response":[168],"time.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2016-06-24T00:00:00"}
