{"id":"https://openalex.org/W2135290016","doi":"https://doi.org/10.1145/1183614.1183644","title":"A document-centric approach to static index pruning in text retrieval systems","display_name":"A document-centric approach to static index pruning in text retrieval systems","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2135290016","doi":"https://doi.org/10.1145/1183614.1183644","mag":"2135290016"},"language":"en","primary_location":{"id":"doi:10.1145/1183614.1183644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","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/A5033673650","display_name":"Stefan B\u00fcttcher","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Stefan B\u00fcttcher","raw_affiliation_strings":["University of Waterloo, Canada","University of Waterloo-Canad\u00e1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo-Canad\u00e1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037737168","display_name":"Charles L. A. Clarke","orcid":"https://orcid.org/0000-0001-8178-9194"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Charles L. A. Clarke","raw_affiliation_strings":["University of Waterloo, Canada","University of Waterloo-Canad\u00e1"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo-Canad\u00e1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033673650"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":27.5406,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.9947201,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9980000257492065,"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":0.9980000257492065,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9961000084877014,"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/T10028","display_name":"Topic Modeling","score":0.9922999739646912,"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/computer-science","display_name":"Computer science","score":0.8356838226318359},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.8036118745803833},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.7297201156616211},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6783000826835632},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6629185676574707},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.5671180486679077},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5185530781745911},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4902217984199524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44252851605415344},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.4323035180568695},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36142683029174805},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.2781355679035187},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09484902024269104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356838226318359},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8036118745803833},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.7297201156616211},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6783000826835632},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6629185676574707},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5671180486679077},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5185530781745911},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4902217984199524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44252851605415344},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.4323035180568695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36142683029174805},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2781355679035187},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09484902024269104},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1183614.1183644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM international conference on Information and knowledge management  - CIKM '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.9474","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.9474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://stefan.buettcher.org/papers/buettcher_2006_static_index_pruning.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W7157229","https://openalex.org/W19293941","https://openalex.org/W95284390","https://openalex.org/W1505880430","https://openalex.org/W1973520416","https://openalex.org/W2006608770","https://openalex.org/W2006997130","https://openalex.org/W2009346361","https://openalex.org/W2034117506","https://openalex.org/W2038807029","https://openalex.org/W2065472179","https://openalex.org/W2125203709","https://openalex.org/W2126782364","https://openalex.org/W2135050452"],"related_works":["https://openalex.org/W2124379162","https://openalex.org/W2805651586","https://openalex.org/W168472812","https://openalex.org/W2611406449","https://openalex.org/W2520801971","https://openalex.org/W4246128701","https://openalex.org/W2189581250","https://openalex.org/W2018548360","https://openalex.org/W47271624","https://openalex.org/W2138197496"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,17,23,26,74,98],"static":[3],"index":[4,33,68,87],"pruning":[5,121],"method,":[6],"to":[7,20,45,62,84,90,117],"be":[8,60],"used":[9,61],"in":[10,31,77,112],"ad-hoc":[11],"document":[12,134],"retrieval":[13,78],"tasks,":[14],"that":[15],"follows":[16],"document-centric":[18],"approach":[19],"decide":[21],"whether":[22],"posting":[24],"for":[25,102],"given":[27],"term":[28],"should":[29],"remain":[30],"the":[32,42,46,51,64,67,86,94,132],"or":[34],"not.":[35],"The":[36],"decision":[37],"is":[38],"made":[39],"based":[40],"on":[41,131],"term's":[43],"contribution":[44],"document's":[47],"Kullback-Leibler":[48],"divergence":[49],"from":[50],"text":[52,104],"collection's":[53],"global":[54],"language":[55],"model.":[56],"Our":[57],"technique":[58],"can":[59],"decrease":[63,76],"size":[65],"of":[66,97,108,119],"by":[69],"over":[70],"90%,":[71],"at":[72],"only":[73],"minor":[75],"effectiveness.":[79],"It":[80],"thus":[81],"allows":[82],"us":[83],"make":[85],"small":[88],"enough":[89],"fit":[91],"entirely":[92],"into":[93],"main":[95],"memory":[96],"single":[99],"PC,":[100],"even":[101],"large":[103],"collections":[105],"containing":[106],"millions":[107],"documents.":[109],"This":[110],"results":[111],"great":[113],"efficiency":[114],"gains,":[115],"superior":[116],"those":[118],"earlier":[120],"methods,":[122],"and":[123],"an":[124],"average":[125],"response":[126],"time":[127],"around":[128],"20":[129],"ms":[130],"GOV2":[133],"collection.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}