{"id":"https://openalex.org/W2149530645","doi":"https://doi.org/10.1145/2009916.2009992","title":"Inverted indexes for phrases and strings","display_name":"Inverted indexes for phrases and strings","publication_year":2011,"publication_date":"2011-07-24","ids":{"openalex":"https://openalex.org/W2149530645","doi":"https://doi.org/10.1145/2009916.2009992","mag":"2149530645"},"language":"en","primary_location":{"id":"doi:10.1145/2009916.2009992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2009992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110582646","display_name":"Manish Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Patil","raw_affiliation_strings":["Louisiana State University, Baton Rouge, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University, Baton Rouge, LA, USA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049669178","display_name":"Sharma V. Thankachan","orcid":"https://orcid.org/0000-0002-6852-1035"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharma V. Thankachan","raw_affiliation_strings":["Louisiana State University, Baton Rouge, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University, Baton Rouge, LA, USA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105778361","display_name":"Rahul Shah","orcid":"https://orcid.org/0000-0002-0605-5681"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Shah","raw_affiliation_strings":["Louisiana State University, Baton Rouge, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University, Baton Rouge, LA, USA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013112058","display_name":"Wing-Kai Hon","orcid":"https://orcid.org/0000-0002-0570-2904"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wing-Kai Hon","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan Roc","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003340402","display_name":"Jeffrey Scott Vitter","orcid":"https://orcid.org/0000-0001-7970-6118"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Scott Vitter","raw_affiliation_strings":["The University of Kansas, Lawrence, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Kansas, Lawrence, KS, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009209511","display_name":"Sabrina Chandrasekaran","orcid":null},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sabrina Chandrasekaran","raw_affiliation_strings":["Louisiana State University, Baton Rouge, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University, Baton Rouge, LA, USA","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.8235,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.9826495,"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":"555","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9898999929428101,"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/T12029","display_name":"DNA and Biological Computing","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.9355243444442749},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.9173400402069092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7395403385162354},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.679002046585083},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6633421182632446},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6285772919654846},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.5927780270576477},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5355181097984314},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47628965973854065},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.42908406257629395},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40361806750297546},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.38515061140060425},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30995386838912964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29525473713874817},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.16908177733421326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16707900166511536}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9355243444442749},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.9173400402069092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395403385162354},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.679002046585083},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6633421182632446},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6285772919654846},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5927780270576477},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5355181097984314},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47628965973854065},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.42908406257629395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40361806750297546},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38515061140060425},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30995386838912964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29525473713874817},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.16908177733421326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16707900166511536},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2009916.2009992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2009992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.5521","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.5521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.nthu.edu.tw/~wkhon/papers/PTSHVC11.pdf","raw_type":"text"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3673","is_oa":false,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2671","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.44999998807907104,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W72059462","https://openalex.org/W1501188993","https://openalex.org/W1506856932","https://openalex.org/W1520568851","https://openalex.org/W1534681609","https://openalex.org/W1563036231","https://openalex.org/W1580375125","https://openalex.org/W1608371561","https://openalex.org/W1642710329","https://openalex.org/W1660390307","https://openalex.org/W1672848638","https://openalex.org/W1705815624","https://openalex.org/W1752316941","https://openalex.org/W1876495223","https://openalex.org/W1941715220","https://openalex.org/W1973520416","https://openalex.org/W1981732427","https://openalex.org/W1985174631","https://openalex.org/W2027252317","https://openalex.org/W2051158076","https://openalex.org/W2069153338","https://openalex.org/W2073921136","https://openalex.org/W2085933841","https://openalex.org/W2100970422","https://openalex.org/W2108009052","https://openalex.org/W2127400073","https://openalex.org/W2134696992","https://openalex.org/W2135050452","https://openalex.org/W2138662031","https://openalex.org/W2141957180","https://openalex.org/W2144759920","https://openalex.org/W2146346985","https://openalex.org/W2154803978","https://openalex.org/W2158058909","https://openalex.org/W2170899819","https://openalex.org/W2533248932","https://openalex.org/W3042165818","https://openalex.org/W6618631250","https://openalex.org/W6634736671","https://openalex.org/W6636996047","https://openalex.org/W6637101025","https://openalex.org/W6639465106","https://openalex.org/W6676347795","https://openalex.org/W6679642144","https://openalex.org/W6807072488","https://openalex.org/W6819151042"],"related_works":["https://openalex.org/W2024152506","https://openalex.org/W2149530645","https://openalex.org/W2765525826","https://openalex.org/W2184716188","https://openalex.org/W1981732427","https://openalex.org/W3132814725","https://openalex.org/W2038618507","https://openalex.org/W2101881908","https://openalex.org/W416633688","https://openalex.org/W2166804299"],"abstract_inverted_index":{"Inverted":[0],"indexes":[1,109,137,238],"are":[2,39,75,200,222],"the":[3,23,30,45,52,83,90,96,105,118,132,157,193,228],"most":[4],"fundamental":[5],"and":[6,213,219,261],"widely":[7],"used":[8],"data":[9,97,198],"structures":[10,199],"in":[11,19,32,57,95,156,169,209],"information":[12],"retrieval.":[13,217],"For":[14,231],"each":[15],"unique":[16],"word":[17,35,73],"occurring":[18],"a":[20,27,55,86,161,180,242],"document":[21,154,214],"collection,":[22],"inverted":[24,119,136,158,244],"index":[25,53,81,120,245],"stores":[26],"list":[28,159],"of":[29,48,69,85,108,115,135,160,167,176,211,227],"documents":[31,71],"which":[33,138,177],"this":[34,128,183],"occurs.":[36],"Compression":[37,218],"techniques":[38],"often":[40],"applied":[41],"to":[42,80,103,152,192,202],"further":[43],"reduce":[44],"space":[46,188],"requirement":[47],"these":[49],"lists.":[50],"However,":[51],"has":[54],"shortcoming,":[56],"that":[58,186,236],"only":[59],"predefined":[60],"pattern":[61],"queries":[62],"can":[63],"be":[64],"supported":[65],"efficiently.":[66],"In":[67,127],"terms":[68,210],"string":[70,162,175],"where":[72],"boundaries":[74],"undefined,":[76],"if":[77,100,164],"we":[78,101,130,184,234],"have":[79],"all":[82],"substrings":[84],"given":[87],"document,":[88],"then":[89,117],"storage":[91],"quickly":[92],"becomes":[93],"quadratic":[94],"size.":[98],"Also,":[99],"want":[102],"apply":[104],"same":[106],"type":[107],"for":[110,141,224],"querying":[111],"phrases":[112],"or":[113],"sequence":[114],"words,":[116],"will":[121],"end":[122],"up":[123],"storing":[124],"redundant":[125],"information.":[126],"paper,":[129],"show":[131,185,235,251],"first":[133],"set":[134],"work":[139],"naturally":[140],"strings":[142],"as":[143,145],"well":[144],"phrase":[146,232],"searching.":[147],"The":[148],"central":[149],"idea":[150],"is":[151,171,179,190],"exclude":[153],"d":[155,170],"P":[163,168,178],"every":[165],"occurrence":[166],"subsumed":[172],"by":[173],"another":[174],"prefix.":[181],"With":[182],"our":[187,237],"utilization":[189],"close":[191],"optimal.":[194],"Techniques":[195],"from":[196],"succinct":[197],"deployed":[201],"achieve":[203],"compression":[204],"while":[205],"allowing":[206],"fast":[207],"access":[208],"frequency":[212,260],"id":[215],"based":[216,254],"speed":[220],"trade-offs":[221],"evaluated":[223],"different":[225],"variants":[226],"proposed":[229],"index.":[230],"searching,":[233],"compare":[239],"favorably":[240],"against":[241],"typical":[243],"deploying":[246],"position-wise":[247],"intersections.":[248],"We":[249],"also":[250],"efficient":[252],"top-k":[253],"retrieval":[255],"under":[256],"relevance":[257],"metrics":[258],"like":[259],"tf-idf.":[262]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"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":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}