{"id":"https://openalex.org/W2078251464","doi":"https://doi.org/10.1145/1658377.1658378","title":"Probabilistic static pruning of inverted files","display_name":"Probabilistic static pruning of inverted files","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2078251464","doi":"https://doi.org/10.1145/1658377.1658378","mag":"2078251464"},"language":"en","primary_location":{"id":"doi:10.1145/1658377.1658378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1658377.1658378","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-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/A5021439660","display_name":"Roi Blanco","orcid":null},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Roi Blanco","raw_affiliation_strings":["University of A Coru\u00f1a, Spain","University of A Coruna (Spain)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"University of A Coruna (Spain)","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056469959","display_name":"\u00c1lvaro Barreiro","orcid":"https://orcid.org/0000-0002-6698-2946"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alvaro Barreiro","raw_affiliation_strings":["University of A Coru\u00f1a, Spain","University of A Coruna (Spain)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"University of A Coruna (Spain)","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":null,"apc_paid":null,"fwci":21.9387,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.99239471,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"28","issue":"1","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9993000030517578,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9993000030517578,"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":0.9993000030517578,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9975000023841858,"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/pruning","display_name":"Pruning","score":0.8713458776473999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774486780166626},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7049024105072021},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.6989893913269043},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6465624570846558},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6183429956436157},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5092676877975464},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.45820948481559753},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4331004023551941},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.41643229126930237},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39667215943336487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3860812783241272},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3648107051849365},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.17274636030197144}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8713458776473999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774486780166626},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7049024105072021},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.6989893913269043},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6465624570846558},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6183429956436157},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5092676877975464},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.45820948481559753},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4331004023551941},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.41643229126930237},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39667215943336487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3860812783241272},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3648107051849365},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.17274636030197144},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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":2,"locations":[{"id":"doi:10.1145/1658377.1658378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1658377.1658378","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.348.6042","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.6042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dc.fi.udc.es/%7Eroi/publications/tois2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G27118013","display_name":null,"funder_award_id":"TIN2008-06566-C04-04/TIN","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G8133918581","display_name":null,"funder_award_id":"07SIN005206PR","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W55312212","https://openalex.org/W95791645","https://openalex.org/W135190683","https://openalex.org/W1482214997","https://openalex.org/W1523019309","https://openalex.org/W1535279741","https://openalex.org/W1535624880","https://openalex.org/W1551409364","https://openalex.org/W1554385128","https://openalex.org/W1592871157","https://openalex.org/W1660390307","https://openalex.org/W1828972360","https://openalex.org/W1972594981","https://openalex.org/W1973520416","https://openalex.org/W1985514943","https://openalex.org/W1989468977","https://openalex.org/W2000569744","https://openalex.org/W2003885352","https://openalex.org/W2006997130","https://openalex.org/W2014415866","https://openalex.org/W2015338694","https://openalex.org/W2025345306","https://openalex.org/W2026937586","https://openalex.org/W2027752285","https://openalex.org/W2029533776","https://openalex.org/W2037140704","https://openalex.org/W2043909051","https://openalex.org/W2048045485","https://openalex.org/W2061261643","https://openalex.org/W2065472179","https://openalex.org/W2066238291","https://openalex.org/W2066636486","https://openalex.org/W2072156548","https://openalex.org/W2096411881","https://openalex.org/W2097670688","https://openalex.org/W2102046030","https://openalex.org/W2105157020","https://openalex.org/W2116504754","https://openalex.org/W2123006679","https://openalex.org/W2127899914","https://openalex.org/W2135290016","https://openalex.org/W2138662031","https://openalex.org/W2142510125","https://openalex.org/W2158291389","https://openalex.org/W2160484851","https://openalex.org/W2165612380","https://openalex.org/W2169213601","https://openalex.org/W2621280964","https://openalex.org/W4230607658","https://openalex.org/W4234200495","https://openalex.org/W4246858749","https://openalex.org/W4256046779","https://openalex.org/W6629649570","https://openalex.org/W6637101025"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2040545019","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W2124379162"],"abstract_inverted_index":{"Information":[0],"retrieval":[1,38,167,206],"(IR)":[2],"systems":[3],"typically":[4],"compress":[5],"their":[6,12,60],"indexes":[7],"in":[8,139,172,183],"order":[9],"to":[10,32,37,41,56,59,62,90,125,150],"increase":[11],"efficiency.":[13],"Static":[14],"pruning":[15,45,98,159,195],"is":[16,30,84,101,192,210],"a":[17,63,72,96,104,116,141,194],"form":[18],"of":[19,107,134,180,189,212],"lossy":[20],"data":[21,28],"compression:":[22],"it":[23,176],"removes":[24],"from":[25,49,78,200],"the":[26,34,79,91,111,132,147,152,178,181,201,213],"index,":[27],"that":[29,69,85,100,143,171,197],"estimated":[31],"be":[33,126],"least":[35],"important":[36],"performance,":[39],"according":[40,58],"some":[42],"criterion.":[43,154],"Generally,":[44],"criteria":[46],"are":[47,70,75,124],"derived":[48],"term":[50],"weighting":[51],"functions,":[52],"which":[53,120],"assign":[54],"weights":[55],"terms":[57],"contribution":[61,188],"document's":[64],"contents.":[65],"Usually,":[66],"document-term":[67],"occurrences":[68],"assigned":[71],"low":[73],"weight":[74],"ruled":[76],"out":[77],"index.":[80],"The":[81,128,186],"main":[82,187],"assumption":[83],"those":[86],"entries":[87,123],"contribute":[88],"little":[89],"document":[92],"content.":[93],"We":[94,109,155],"present":[95],"novel":[97],"technique":[99,160,196],"based":[102],"on":[103,161],"probabilistic":[105,205],"model":[106,215],"IR.":[108],"employ":[110],"Probability":[112],"Ranking":[113],"Principle":[114],"as":[115,204],"decision":[117],"criterion":[118],"over":[119],"posting":[121],"list":[122],"pruned.":[127],"proposed":[129,158],"approach":[130],"requires":[131],"estimation":[133],"three":[135],"probabilities,":[136],"combining":[137],"them":[138],"such":[140],"way":[142],"we":[144],"gather":[145],"all":[146],"necessary":[148],"information":[149],"apply":[151],"aforementioned":[153],"evaluate":[156],"our":[157],"five":[162],"TREC":[163],"collections":[164],"and":[165,169,208],"various":[166],"tasks,":[168],"show":[170],"almost":[173],"every":[174],"situation":[175],"outperforms":[177],"state":[179],"art":[182],"index":[184],"pruning.":[185],"this":[190],"work":[191],"proposing":[193],"stems":[198],"directly":[199],"same":[202],"source":[203],"models,":[207],"hence":[209],"independent":[211],"final":[214],"used":[216],"for":[217],"retrieval.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":10}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
