{"id":"https://openalex.org/W2094154930","doi":"https://doi.org/10.1145/1498698.1564507","title":"An experimental investigation of set intersection algorithms for text searching","display_name":"An experimental investigation of set intersection algorithms for text searching","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2094154930","doi":"https://doi.org/10.1145/1498698.1564507","mag":"2094154930"},"language":"en","primary_location":{"id":"doi:10.1145/1498698.1564507","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498698.1564507","pdf_url":null,"source":{"id":"https://openalex.org/S201104086","display_name":"ACM Journal of Experimental Algorithmics","issn_l":"1084-6654","issn":["1084-6654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal of Experimental Algorithmics","raw_type":"journal-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/A5079691449","display_name":"J\u00e9r\u00e9my Barbay","orcid":"https://orcid.org/0000-0002-3392-8353"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"J\u00e9r\u00e9my Barbay","raw_affiliation_strings":["Universidad de Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089947217","display_name":"Alejandro L\u00f3pez-Ort\u00edz","orcid":"https://orcid.org/0000-0003-2671-6173"},"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":"Alejandro L\u00f3pez-Ortiz","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086690493","display_name":"Tyler Lu","orcid":"https://orcid.org/0000-0002-7433-8421"},"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":"Tyler Lu","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046401766","display_name":"Alejandro Salinger","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":false,"raw_author_name":"Alejandro Salinger","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.9654,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.98157949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9977999925613403,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9918000102043152,"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/intersection","display_name":"Intersection (aeronautics)","score":0.8498834371566772},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7040377259254456},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5991260409355164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.592698335647583},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5253826379776001},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4400850236415863},{"id":"https://openalex.org/keywords/randomized-algorithm","display_name":"Randomized algorithm","score":0.43128451704978943},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3806409239768982},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3363747000694275}],"concepts":[{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.8498834371566772},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7040377259254456},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5991260409355164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.592698335647583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5253826379776001},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4400850236415863},{"id":"https://openalex.org/C128669082","wikidata":"https://www.wikidata.org/wiki/Q583461","display_name":"Randomized algorithm","level":2,"score":0.43128451704978943},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3806409239768982},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3363747000694275},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1498698.1564507","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498698.1564507","pdf_url":null,"source":{"id":"https://openalex.org/S201104086","display_name":"ACM Journal of Experimental Algorithmics","issn_l":"1084-6654","issn":["1084-6654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal of Experimental Algorithmics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.176.7133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.176.7133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uwaterloo.ca/%7Eajsaling/papers/fiats.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.3756","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.3756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.dcc.uchile.cl/~jbarbay/MyPublications/2009-JEA-AnExperimentalInvestigationOfSetIntersectionAlgorithmsForTextSearching-BarbayLopezOrtizLuSalinger.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.507.7938","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.507.7938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utoronto.ca/~tl/papers/fiats.pdf","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":15,"referenced_works":["https://openalex.org/W1490473477","https://openalex.org/W1533079463","https://openalex.org/W1542353629","https://openalex.org/W1556741196","https://openalex.org/W1561988317","https://openalex.org/W1975489634","https://openalex.org/W1988690071","https://openalex.org/W2001345341","https://openalex.org/W2053550438","https://openalex.org/W2063039343","https://openalex.org/W2069153338","https://openalex.org/W2071001390","https://openalex.org/W2100474856","https://openalex.org/W2161420356","https://openalex.org/W6839964580"],"related_works":["https://openalex.org/W1965604548","https://openalex.org/W2357241418","https://openalex.org/W2946979626","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2093689493","https://openalex.org/W3022131925","https://openalex.org/W2385407215","https://openalex.org/W4308642228"],"abstract_inverted_index":{"The":[0],"intersection":[1,34,47,82],"of":[2,13,16,35,145,148,156,211,214],"large":[3],"ordered":[4],"sets":[5],"is":[6],"a":[7,20,115,121],"common":[8],"problem":[9],"in":[10,39,45,75,143,154,175,206,209],"the":[11,14,33,46,55,58,81,99,107,125,140,146,157,169,212],"context":[12,178],"evaluation":[15],"boolean":[17],"queries":[18,109],"to":[19,193],"search":[21,202],"engine.":[22],"In":[23,196],"this":[24],"article,":[25],"we":[26,77,198],"propose":[27],"several":[28],"improved":[29],"algorithms":[30,56,203],"for":[31,41],"computing":[32],"sorted":[36,43],"arrays,":[37],"and":[38,64,68,71,79,86,90,105,120,150,153,184,190],"particular":[40],"searching":[42],"arrays":[44],"context.":[48],"We":[49,96,138],"perform":[50,204],"an":[51],"experimental":[52],"comparison":[53],"with":[54,133],"from":[57,61,69,84,103,124,171],"previous":[59,173],"studies":[60,174],"Demaine,":[62],"L\u00f3pez-Ortiz,":[63],"Munro":[65],"[ALENEX":[66],"2001]":[67],"Baeza-Yates":[70,104],"Salinger":[72],"[SPIRE":[73],"2005];":[74],"addition,":[76],"implement":[78],"test":[80],"algorithm":[83],"Barbay":[85],"Kenyon":[87],"[SODA":[88],"2002]":[89],"its":[91,134],"randomized":[92],"variant":[93],"[SAGA":[94],"2003].":[95],"consider":[97],"both":[98,142,172],"random":[100,188],"data":[101],"set":[102],"Salinger,":[106],"Google":[108],"used":[110],"by":[111,118],"Demaine":[112],"et":[113],"al.,":[114],"corpus":[116,123],"provided":[117],"Google,":[119],"larger":[122],"TREC":[126],"Terabyte":[127],"2006":[128],"efficiency":[129],"query":[130,136],"stream,":[131],"along":[132],"own":[135],"log.":[137],"measure":[139],"performance":[141],"terms":[144,155,210],"number":[147,213],"comparisons":[149,215],"searches":[151],"performed,":[152],"CPU":[158,185],"time":[159],"on":[160,181,187],"two":[161],"different":[162],"architectures.":[163],"Our":[164],"results":[165,170],"confirm":[166],"or":[167],"improve":[168],"their":[176],"respective":[177],"(comparison":[179],"model":[180],"real":[182],"data,":[183],"measures":[186],"data)":[189],"extend":[191],"them":[192],"new":[194],"contexts.":[195],"particular,":[197],"show":[199],"that":[200],"value-based":[201],"well":[205],"posting":[207],"lists":[208],"performed.":[216]},"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":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
