{"id":"https://openalex.org/W2111046826","doi":"https://doi.org/10.1145/2348283.2348317","title":"Efficient in-memory top-k document retrieval","display_name":"Efficient in-memory top-k document retrieval","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2111046826","doi":"https://doi.org/10.1145/2348283.2348317","mag":"2111046826"},"language":"en","primary_location":{"id":"doi:10.1145/2348283.2348317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2348283.2348317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th 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/A5070937840","display_name":"J. Shane Culpepper","orcid":"https://orcid.org/0000-0002-1902-9087"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"J. Shane Culpepper","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086980890","display_name":"Matthias Petri","orcid":"https://orcid.org/0000-0002-0054-9429"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Matthias Petri","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085925326","display_name":"Falk Scholer","orcid":"https://orcid.org/0000-0001-9094-0810"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Falk Scholer","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070937840"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":9.2818,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.97896204,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8789762258529663},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.8104795217514038},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7942287921905518},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6549808979034424},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5882390141487122},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.47223353385925293},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.44547489285469055},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4447951018810272},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43014687299728394},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4232948422431946},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.42324525117874146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28085845708847046},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1025664210319519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8789762258529663},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.8104795217514038},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7942287921905518},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6549808979034424},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5882390141487122},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.47223353385925293},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.44547489285469055},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4447951018810272},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43014687299728394},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4232948422431946},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.42324525117874146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28085845708847046},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1025664210319519},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2348283.2348317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2348283.2348317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.61RMIT_INST:11246681920001341","is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=2348317","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W27682417","https://openalex.org/W127947978","https://openalex.org/W142567295","https://openalex.org/W1482214997","https://openalex.org/W1494592156","https://openalex.org/W1504934817","https://openalex.org/W1509991416","https://openalex.org/W1516527356","https://openalex.org/W1546195864","https://openalex.org/W1593203859","https://openalex.org/W1752316941","https://openalex.org/W1860074289","https://openalex.org/W1965853364","https://openalex.org/W1973520416","https://openalex.org/W1976682045","https://openalex.org/W1985174631","https://openalex.org/W1991360400","https://openalex.org/W2007791040","https://openalex.org/W2014318353","https://openalex.org/W2025690557","https://openalex.org/W2030431619","https://openalex.org/W2041445031","https://openalex.org/W2044031164","https://openalex.org/W2051158076","https://openalex.org/W2065472179","https://openalex.org/W2066667100","https://openalex.org/W2088386938","https://openalex.org/W2096575760","https://openalex.org/W2123006679","https://openalex.org/W2124213360","https://openalex.org/W2125203709","https://openalex.org/W2134696992","https://openalex.org/W2135050452","https://openalex.org/W2138662031","https://openalex.org/W2141957180","https://openalex.org/W2144759920","https://openalex.org/W2151453116","https://openalex.org/W2154610494","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2159647614","https://openalex.org/W2161488606","https://openalex.org/W2163652601","https://openalex.org/W2263798363","https://openalex.org/W2295820528","https://openalex.org/W3124327069","https://openalex.org/W4250452878"],"related_works":["https://openalex.org/W2058987221","https://openalex.org/W2145657320","https://openalex.org/W2102493899","https://openalex.org/W2389273994","https://openalex.org/W4282568653","https://openalex.org/W2187610212","https://openalex.org/W2003608043","https://openalex.org/W2123678380","https://openalex.org/W180545237","https://openalex.org/W1837234277"],"abstract_inverted_index":{"For":[0],"over":[1],"forty":[2],"years":[3],"the":[4,14,83,88,96],"dominant":[5],"data":[6,33,92],"structure":[7],"for":[8,21,31,71,100,158],"ranked":[9,75],"document":[10,25,76],"retrieval":[11,26,77],"has":[12],"been":[13],"inverted":[15,118],"index.":[16],"Inverted":[17],"indexes":[18],"are":[19],"effective":[20],"a":[22,56,67,79,159],"variety":[23,160],"of":[24,58,161],"tasks,":[27],"and":[28,40,87,94,122,138,156],"particularly":[29],"efficient":[30,102],"large":[32],"collection":[34],"scenarios":[35],"that":[36,129,146],"require":[37],"disk":[38],"access":[39],"storage.":[41],"However,":[42],"many":[43],"efficiency-bound":[44],"search":[45,163],"tasks":[46],"can":[47,147],"now":[48],"easily":[49],"be":[50,148],"supported":[51],"entirely":[52,104],"in":[53],"memory":[54],"as":[55],"result":[57],"recent":[59],"hardware":[60],"advances.":[61],"In":[62],"this":[63],"paper":[64],"we":[65],"present":[66],"hybrid":[68],"algorithmic":[69,98],"framework":[70,131],"in-memory":[72],"bag":[73],"of-words":[74],"using":[78,117],"self-index":[80],"derived":[81],"from":[82],"FM-Index,":[84],"wavelet":[85],"tree,":[86],"compressed":[89],"suffix":[90],"tree":[91],"structures,":[93,137],"evaluate":[95],"various":[97],"trade-offs":[99],"performing":[101],"queries":[103,116],"in-memory.":[105],"We":[106,127],"compare":[107],"our":[108,130,144],"approach":[109],"with":[110,134],"two":[111],"classic":[112],"approaches":[113],"to":[114,153],"bag-of-words":[115],"indexes,":[119],"term-at-a-time":[120],"(TAAT)":[121],"document-at-a-time":[123],"(DAAT)":[124],"query":[125],"processing.":[126],"show":[128],"is":[132],"competitive":[133],"state-of-the-art":[135],"indexing":[136],"describe":[139],"new":[140],"capabilities":[141],"provided":[142],"by":[143,150],"algorithms":[145],"leveraged":[149],"future":[151],"systems":[152],"improve":[154],"effectiveness":[155],"efficiency":[157],"fundamental":[162],"operations.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}