{"id":"https://openalex.org/W2127667244","doi":"https://doi.org/10.1145/1526709.1526770","title":"Compressed web indexes","display_name":"Compressed web indexes","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2127667244","doi":"https://doi.org/10.1145/1526709.1526770","mag":"2127667244"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526770","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/A5078401676","display_name":"Flavio Chierichetti","orcid":"https://orcid.org/0000-0001-8261-9058"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Flavio Chierichetti","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy","Sapienza university of Rome, Rome, Italy#TAB#"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza university of Rome, Rome, Italy#TAB#","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107809381","display_name":"Ravi Kumar","orcid":null},"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":"Ravi Kumar","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078491738","display_name":"Prabhakar Raghavan","orcid":"https://orcid.org/0000-0001-9853-7604"},"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":"Prabhakar Raghavan","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":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078401676"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":4.0546,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94052099,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"451","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9988999962806702,"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":0.9975000023841858,"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/zipfs-law","display_name":"Zipf's law","score":0.9698209166526794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.730309247970581},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5515324473381042},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5487039685249329},{"id":"https://openalex.org/keywords/pareto-distribution","display_name":"Pareto distribution","score":0.5201138257980347},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.47635769844055176},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4737618565559387},{"id":"https://openalex.org/keywords/heavy-tailed-distribution","display_name":"Heavy-tailed distribution","score":0.4645884335041046},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.45056524872779846},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3817339837551117},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3291369080543518},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20504271984100342},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1392088532447815},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11398464441299438}],"concepts":[{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.9698209166526794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730309247970581},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5515324473381042},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5487039685249329},{"id":"https://openalex.org/C190373308","wikidata":"https://www.wikidata.org/wiki/Q837683","display_name":"Pareto distribution","level":2,"score":0.5201138257980347},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.47635769844055176},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4737618565559387},{"id":"https://openalex.org/C1602530","wikidata":"https://www.wikidata.org/wiki/Q1472677","display_name":"Heavy-tailed distribution","level":3,"score":0.4645884335041046},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.45056524872779846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3817339837551117},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3291369080543518},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20504271984100342},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1392088532447815},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11398464441299438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1526709.1526770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526770","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.6018","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.6018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2009.org/proceedings/pdf/p451.pdf","raw_type":"text"},{"id":"pmh:oai:iris.uniroma1.it:11573/497780","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/497780","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W120264976","https://openalex.org/W191231183","https://openalex.org/W1495550473","https://openalex.org/W1509465553","https://openalex.org/W1517590677","https://openalex.org/W1532325895","https://openalex.org/W1535065339","https://openalex.org/W1574901103","https://openalex.org/W1605433909","https://openalex.org/W1660390307","https://openalex.org/W1669813703","https://openalex.org/W1991549091","https://openalex.org/W1994727615","https://openalex.org/W2015662797","https://openalex.org/W2016743875","https://openalex.org/W2017392697","https://openalex.org/W2036671379","https://openalex.org/W2052867877","https://openalex.org/W2057464142","https://openalex.org/W2061491895","https://openalex.org/W2075261997","https://openalex.org/W2079656678","https://openalex.org/W2116207470","https://openalex.org/W2144219418","https://openalex.org/W2147824439","https://openalex.org/W2151626491","https://openalex.org/W2156891755","https://openalex.org/W2160484851","https://openalex.org/W2170521549","https://openalex.org/W2621280964","https://openalex.org/W4210634265","https://openalex.org/W4240241513","https://openalex.org/W4240908132","https://openalex.org/W4365806327","https://openalex.org/W6629589361","https://openalex.org/W6631875860","https://openalex.org/W6637101025","https://openalex.org/W6670271065","https://openalex.org/W6677085841","https://openalex.org/W6682042974"],"related_works":["https://openalex.org/W2954657388","https://openalex.org/W2039455518","https://openalex.org/W105352677","https://openalex.org/W1004791718","https://openalex.org/W2309045634","https://openalex.org/W4300602132","https://openalex.org/W2911842713","https://openalex.org/W1896412130","https://openalex.org/W4366827547","https://openalex.org/W3185970707"],"abstract_inverted_index":{"Web":[0,207],"search":[1],"engines":[2],"use":[3],"indexes":[4,25,62,104,139],"to":[5,18,122,146,171,195],"efficiently":[6],"retrieve":[7],"pages":[8,16],"containing":[9],"specified":[10,19],"query":[11],"terms,":[12],"as":[13,15],"well":[14,56,194],"linking":[17],"pages.":[20],"The":[21],"problem":[22],"of":[23,102,136,149,151,168,184],"compressed":[24],"that":[26,40,63,89,108,120,153,165],"permit":[27],"such":[28,61],"fast":[29,65],"retrieval":[30],"has":[31],"a":[32,47,52,80,117,128,173],"long":[33],"history.":[34],"We":[35,94],"consider":[36],"the":[37,41,71,74,87,92,99,113,133,166,186,191,203],"problem:":[38],"assuming":[39],"terms":[42,169],"in":[43,138,156,190],"(or":[44,79],"links":[45],"to)":[46],"page":[48],"are":[49,86,154],"generated":[50],"from":[51],"probability":[53,75,124],"distribution,":[54,125],"how":[55],"compactly":[57],"can":[58],"we":[59,115],"build":[60],"allow":[64],"retrieval?":[66],"Of":[67],"particular":[68],"interest":[69],"is":[70,77,132,200],"case":[72],"when":[73],"distribution":[76,167],"Zipfian":[78],"similar":[81],"power":[82,129],"law),":[83],"since":[84],"these":[85],"distributions":[88],"arise":[90],"on":[91,98,160],"web.":[93],"obtain":[95],"sharp":[96],"bounds":[97,144],"space":[100],"requirement":[101],"Boolean":[103],"for":[105],"text":[106],"documents":[107],"follow":[109,172],"Zipf's":[110,178],"law.":[111,179],"In":[112],"process":[114],"develop":[116],"general":[118],"technique":[119],"applies":[121],"any":[123],"not":[126],"necessarily":[127],"law;":[130],"this":[131],"first":[134],"analysis":[135],"compression":[137],"under":[140],"arbitrary":[141],"distributions.":[142],"Our":[143,158],"lead":[145],"quantitative":[147],"versions":[148],"rules":[150],"thumb":[152],"folklore":[155],"indexing.":[157],"experiments":[159,192],"several":[161],"document":[162],"collections":[163],"show":[164],"appears":[170],"double-Pareto":[174],"law":[175],"rather":[176],"than":[177],"Despite":[180],"widely":[181],"varying":[182],"sets":[183],"documents,":[185],"index":[187],"sizes":[188],"observed":[189],"conform":[193],"our":[196],"theoretical":[197],"predictions.":[198],"Copyright":[199],"held":[201],"by":[202],"International":[204],"World":[205],"Wide":[206],"Conference":[208],"Committee":[209],"(IW3C2).":[210]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}