{"id":"https://openalex.org/W2127899914","doi":"https://doi.org/10.1145/1277741.1277776","title":"Pruning policies for two-tiered inverted index with correctness guarantee","display_name":"Pruning policies for two-tiered inverted index with correctness guarantee","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2127899914","doi":"https://doi.org/10.1145/1277741.1277776","mag":"2127899914"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277776","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/A5030400740","display_name":"Alexandros Ntoulas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandros Ntoulas","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073859348","display_name":"Junghoo Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junghoo Cho","raw_affiliation_strings":["UCLA","UCLA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]},{"raw_affiliation_string":"UCLA ,","institution_ids":["https://openalex.org/I2799798094"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1139,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98375185,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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":0.9948999881744385,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.993399977684021,"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/inverted-index","display_name":"Inverted index","score":0.7821170687675476},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.7730370759963989},{"id":"https://openalex.org/keywords/notice","display_name":"Notice","score":0.7496349811553955},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7474662065505981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7407768964767456},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6515854597091675},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5965667366981506},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5381553769111633},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4763788878917694},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4297252297401428},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.4210089147090912},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37598633766174316},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32787612080574036},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.23229381442070007},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19912055134773254},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15952914953231812},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.10004323720932007}],"concepts":[{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.7821170687675476},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.7730370759963989},{"id":"https://openalex.org/C2779913896","wikidata":"https://www.wikidata.org/wiki/Q7063001","display_name":"Notice","level":2,"score":0.7496349811553955},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7474662065505981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407768964767456},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6515854597091675},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5965667366981506},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5381553769111633},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4763788878917694},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4297252297401428},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.4210089147090912},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37598633766174316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32787612080574036},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.23229381442070007},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19912055134773254},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15952914953231812},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.10004323720932007},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1277741.1277776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277776","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:10.1.1.329.7088","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.7088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.sch.gr/lakritid/meetings/pruning_inverted_index.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.4274","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.4274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://oak.cs.ucla.edu/~cho/papers/ntoulas-sigir07.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1500117362","https://openalex.org/W1535279741","https://openalex.org/W1660390307","https://openalex.org/W1845137714","https://openalex.org/W1850437073","https://openalex.org/W1854214752","https://openalex.org/W1956559956","https://openalex.org/W1977841655","https://openalex.org/W1978063867","https://openalex.org/W1985986751","https://openalex.org/W1991360400","https://openalex.org/W2000568172","https://openalex.org/W2006997130","https://openalex.org/W2043909051","https://openalex.org/W2059387258","https://openalex.org/W2066055909","https://openalex.org/W2080676333","https://openalex.org/W2086453025","https://openalex.org/W2095849344","https://openalex.org/W2096041903","https://openalex.org/W2098025050","https://openalex.org/W2099797738","https://openalex.org/W2116504754","https://openalex.org/W2132107871","https://openalex.org/W2134206624","https://openalex.org/W2135050452","https://openalex.org/W2135290016","https://openalex.org/W2138621811","https://openalex.org/W2139611552","https://openalex.org/W2149397822","https://openalex.org/W2157748587","https://openalex.org/W2164520297","https://openalex.org/W2164806720","https://openalex.org/W2666600683","https://openalex.org/W2999905431","https://openalex.org/W3003506064","https://openalex.org/W3145128584","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W118734887","https://openalex.org/W1940136973","https://openalex.org/W2117332447","https://openalex.org/W1601704076","https://openalex.org/W2084064431","https://openalex.org/W2461782657","https://openalex.org/W2413339343","https://openalex.org/W2119135658","https://openalex.org/W2161902337","https://openalex.org/W2137250554"],"abstract_inverted_index":{"The":[0],"Web":[1],"search":[2,32,131],"engines":[3,33],"maintain":[4],"large-scale":[5],"inverted":[6],"indexes":[7],"which":[8],"are":[9,41],"queried":[10],"thousands":[11],"of":[12,29,59,71],"times":[13],"per":[14],"second":[15],"by":[16,67],"users":[17],"eager":[18],"for":[19],"information.":[20],"In":[21],"order":[22],"to":[23,37,43,54],"cope":[24],"with":[25],"the":[26,56,69,72,77,82,92,101,109,117,121,125,129],"vast":[27],"amounts":[28],"query":[30],"loads,":[31],"prune":[34],"their":[35],"index":[36,53,84],"keep":[38],"documents":[39],"that":[40],"likely":[42],"be":[44,99,114],"returned":[45],"as":[46],"top":[47,78,102],"results,":[48],"and":[49],"use":[50],"this":[51,62,133],"pruned":[52,83,110,122],"compute":[55,76],"first":[57],"batches":[58],"results.":[60],"While":[61],"approach":[63],"can":[64],"improve":[65],"performance":[66],"reducing":[68],"size":[70],"index,":[73,111],"if":[74,95],"we":[75,85],"results":[79,103,118],"only":[80],"from":[81,120],"may":[86],"notice":[87],"a":[88,96],"significant":[89],"degradation":[90],"in":[91,100,108,128],"result":[93],"quality:":[94],"document":[97],"should":[98],"but":[104],"was":[105],"not":[106],"included":[107],"it":[112],"will":[113],"placed":[115],"behind":[116],"computed":[119],"index.":[123],"Given":[124],"fierce":[126],"competition":[127],"online":[130],"market,":[132],"phenomenon":[134],"is":[135],"clearly":[136],"undesirable.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}