{"id":"https://openalex.org/W2133953554","doi":"https://doi.org/10.1145/1277741.1277855","title":"Heavy-tailed distributions and multi-keyword queries","display_name":"Heavy-tailed distributions and multi-keyword queries","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2133953554","doi":"https://doi.org/10.1145/1277741.1277855","mag":"2133953554"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277855","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/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016543371","display_name":"Kenneth Church","orcid":"https://orcid.org/0000-0001-8378-6069"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Church","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034735876","display_name":"Arnd Christian K\u00f6nig","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnd Christian K\u00f6nig","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110377641","display_name":"Liying Sui","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liying Sui","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038037154"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.2385,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.92755441,"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":"663","last_page":"670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9976000189781189,"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":0.9976000189781189,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9962000250816345,"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":0.9958000183105469,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8429287672042847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8215717673301697},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.804659366607666},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.691265344619751},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6861577033996582},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6733273863792419},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5331840515136719},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.50716233253479},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15676385164260864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11386603116989136},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1056952178478241}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8429287672042847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215717673301697},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.804659366607666},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.691265344619751},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6861577033996582},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6733273863792419},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5331840515136719},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.50716233253479},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15676385164260864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11386603116989136},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1056952178478241},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1277741.1277855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277855","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:10.1.1.92.4296","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.92.4296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/~chrisko/papers/sigir07.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1565494300","https://openalex.org/W1589049940","https://openalex.org/W1672197616","https://openalex.org/W1981732427","https://openalex.org/W1991360400","https://openalex.org/W2006608770","https://openalex.org/W2016185430","https://openalex.org/W2115054880","https://openalex.org/W2130484710","https://openalex.org/W2135050452","https://openalex.org/W2160484851","https://openalex.org/W2621280964"],"related_works":["https://openalex.org/W3123832408","https://openalex.org/W2393932274","https://openalex.org/W2102493899","https://openalex.org/W2145657320","https://openalex.org/W4282568653","https://openalex.org/W2187610212","https://openalex.org/W2123678380","https://openalex.org/W180545237","https://openalex.org/W2155791520","https://openalex.org/W1514026108"],"abstract_inverted_index":{"Intersecting":[0],"inverted":[1],"indexes":[2,74,99],"is":[3,20],"a":[4,24],"fundamental":[5],"operation":[6,19],"for":[7,17,27],"many":[8],"applications":[9,38],"in":[10,35,118],"information":[11],"retrieval":[12],"and":[13,49],"databases.":[14],"Efficient":[15],"indexing":[16],"this":[18],"known":[21,45],"to":[22,55,102],"be":[23,107],"hard":[25],"problem":[26],"arbitrary":[28,83,104],"data":[29],"distributions.":[30],"However,":[31],"text":[32],"corpora":[33],"used":[34],"Information":[36],"Retrieval":[37],"often":[39],"have":[40],"convenient":[41],"power-law":[42],"constraints":[43],"(also":[44],"as":[46],"Zipf\u2019s":[47],"Law":[48],"long":[50],"tails)":[51],"that":[52,97],"allow":[53],"us":[54],"materialize":[56],"carefully":[57],"chosen":[58],"combinations":[59],"of":[60,78,92,100,115],"multi-keyword":[61,73],"indexes,":[62],"which":[63],"significantly":[64],"improve":[65],"worst-case":[66],"performance":[67],"without":[68],"requiring":[69],"excessive":[70],"storage.":[71],"These":[72],"limit":[75],"the":[76,98,116,119],"number":[77],"postings":[79,117],"accessed":[80],"when":[81],"computing":[82],"index":[84],"intersections.":[85],"Our":[86],"evaluation":[87],"on":[88],"an":[89],"e-commerce":[90],"collection":[91],"20":[93,113],"million":[94],"products":[95],"shows":[96],"up":[101],"four":[103],"keywords":[105],"can":[106],"intersected":[108],"while":[109],"accessing":[110],"less":[111],"than":[112],"%":[114],"largest":[120],"single-keyword":[121],"index.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"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":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}