{"id":"https://openalex.org/W2152437528","doi":"https://doi.org/10.1145/1526709.1526764","title":"Inverted index compression and query processing with optimized document ordering","display_name":"Inverted index compression and query processing with optimized document ordering","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2152437528","doi":"https://doi.org/10.1145/1526709.1526764","mag":"2152437528"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","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/A5101914876","display_name":"Hao Yan","orcid":"https://orcid.org/0000-0002-7468-528X"},"institutions":[{"id":"https://openalex.org/I90965887","display_name":"SUNY Polytechnic Institute","ror":"https://ror.org/000fxgx19","country_code":"US","type":"education","lineage":["https://openalex.org/I90965887"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Yan","raw_affiliation_strings":["Polytechnic Institute of NYU, Brooklyn, NY, USA"],"affiliations":[{"raw_affiliation_string":"Polytechnic Institute of NYU, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I90965887"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078621623","display_name":"Shuai Ding","orcid":"https://orcid.org/0009-0001-2744-3018"},"institutions":[{"id":"https://openalex.org/I90965887","display_name":"SUNY Polytechnic Institute","ror":"https://ror.org/000fxgx19","country_code":"US","type":"education","lineage":["https://openalex.org/I90965887"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Ding","raw_affiliation_strings":["Polytechnic Institute of NYU, Brooklyn, NY, USA"],"affiliations":[{"raw_affiliation_string":"Polytechnic Institute of NYU, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I90965887"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074323303","display_name":"Torsten Suel","orcid":"https://orcid.org/0000-0002-8324-980X"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Torsten Suel","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101914876"],"corresponding_institution_ids":["https://openalex.org/I90965887"],"apc_list":null,"apc_paid":null,"fwci":33.8722,"has_fulltext":false,"cited_by_count":278,"citation_normalized_percentile":{"value":0.99786414,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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":0.9983999729156494,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057601451873779},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.7561801671981812},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.618192195892334},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5726200938224792},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5716648101806641},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5485305786132812},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5161955952644348},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47761625051498413},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.26905712485313416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22924339771270752},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07605820894241333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057601451873779},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.7561801671981812},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.618192195892334},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5726200938224792},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5716648101806641},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5485305786132812},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5161955952644348},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47761625051498413},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.26905712485313416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22924339771270752},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07605820894241333},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1526709.1526764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1483194439","https://openalex.org/W1495124840","https://openalex.org/W1524501441","https://openalex.org/W1552628010","https://openalex.org/W1556744446","https://openalex.org/W1559631118","https://openalex.org/W1575155361","https://openalex.org/W1669813703","https://openalex.org/W1964338930","https://openalex.org/W1965172494","https://openalex.org/W1975965284","https://openalex.org/W1985986751","https://openalex.org/W2022292926","https://openalex.org/W2038807029","https://openalex.org/W2042130547","https://openalex.org/W2052867877","https://openalex.org/W2066636486","https://openalex.org/W2076471773","https://openalex.org/W2111215543","https://openalex.org/W2116504754","https://openalex.org/W2121672615","https://openalex.org/W2135050452","https://openalex.org/W2138662031","https://openalex.org/W2140453381","https://openalex.org/W2144193618","https://openalex.org/W2154610494","https://openalex.org/W2160484851","https://openalex.org/W2170907470","https://openalex.org/W2427788461","https://openalex.org/W2621280964"],"related_works":["https://openalex.org/W1512321724","https://openalex.org/W4231317009","https://openalex.org/W2367696392","https://openalex.org/W4383723869","https://openalex.org/W4293703255","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W2271907651","https://openalex.org/W3007688875","https://openalex.org/W2110517301"],"abstract_inverted_index":{"Web":[0],"search":[1],"engines":[2],"use":[3],"highly":[4],"optimized":[5],"compression":[6,20,55,66,76,114,128,147],"schemes":[7],"to":[8,68,112],"decrease":[9],"inverted":[10],"index":[11,19,65,75,183],"size":[12,184],"and":[13,17,51,77,108,116,133,148,154,185],"improve":[14,64],"query":[15,78,117,173,186],"throughput,":[16],"many":[18],"techniques":[21,80,129,139,156],"have":[22],"been":[23],"studied":[24],"in":[25,43,145,182],"the":[26,40,44,91,167,190],"literature.":[27],"One":[28],"approach":[29,171],"taken":[30],"by":[31],"several":[32],"recent":[33],"studies":[34],"first":[35],"performs":[36],"a":[37,69],"renumbering":[38],"of":[39,95,127,137,169,194],"document":[41,71,131],"IDs":[42,132],"collection":[45,193],"that":[46,60,101],"groups":[47],"similar":[48],"documents":[49],"together,":[50],"then":[52],"applies":[53],"standard":[54],"techniques.":[56],"It":[57],"is":[58,105],"known":[59],"this":[61,120,162,170],"can":[62,141],"significantly":[63],"compared":[67],"random":[70],"ordering.":[72],"We":[73,122,151],"study":[74,126,166],"processing":[79,118,174,187],"for":[81,119,130,157,161],"such":[82,102],"reordered":[83],"indexes.":[84],"Previous":[85],"work":[86],"has":[87],"focused":[88],"on":[89,110,172,189],"determining":[90],"best":[92],"possible":[93],"ordering":[94,104],"documents.":[96],"In":[97],"contrast,":[98],"we":[99,165],"assume":[100],"an":[103,124],"already":[106],"given,":[107],"focus":[109],"how":[111],"optimize":[113],"methods":[115],"case.":[121,163],"perform":[123],"extensive":[125],"present":[134],"new":[135],"optimizations":[136],"existing":[138],"which":[140],"achieve":[142],"significant":[143,180],"improvement":[144],"both":[146],"decompression":[149],"performances.":[150],"also":[152],"propose":[153],"evaluate":[155],"compressing":[158],"frequency":[159],"values":[160],"Finally,":[164],"effect":[168],"performance.":[175],"Our":[176],"experiments":[177],"show":[178],"very":[179],"improvements":[181],"speed":[188],"TREC":[191],"GOV2":[192],"25.2":[195],"million":[196],"web":[197],"pages.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":31},{"year":2012,"cited_by_count":30}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}