{"id":"https://openalex.org/W2345228340","doi":"https://doi.org/10.1145/2836166","title":"Sparse Text Indexing in Small Space","display_name":"Sparse Text Indexing in Small Space","publication_year":2016,"publication_date":"2016-04-25","ids":{"openalex":"https://openalex.org/W2345228340","doi":"https://doi.org/10.1145/2836166","mag":"2345228340"},"language":"en","primary_location":{"id":"doi:10.1145/2836166","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2836166","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"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 Transactions on Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbit.dtu.dk/en/publications/820ab6bf-15a4-4dc7-984d-757deb3d37dd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083100766","display_name":"Philip Bille","orcid":"https://orcid.org/0000-0002-1120-5154"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Philip Bille","raw_affiliation_strings":["Technical University of Denmark, DTU Compute, Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark, DTU Compute, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055443993","display_name":"Johannes Fischer","orcid":"https://orcid.org/0000-0002-3384-597X"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Fischer","raw_affiliation_strings":["TU Dortmund, Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"TU Dortmund, Department of Computer Science","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070148734","display_name":"Inge Li G\u00f8rtz","orcid":"https://orcid.org/0000-0002-8322-4952"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Inge Li G\u00f8rtz","raw_affiliation_strings":["Technical University of Denmark, DTU Compute, Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark, DTU Compute, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028866207","display_name":"Tsvi Kopelowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I53964585","display_name":"Weizmann Institute of Science","ror":"https://ror.org/0316ej306","country_code":"IL","type":"education","lineage":["https://openalex.org/I53964585"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tsvi Kopelowitz","raw_affiliation_strings":["Weizmann Institute of Science, Faculty of Mathematics and Computer Science, Rehovot, Israel"],"affiliations":[{"raw_affiliation_string":"Weizmann Institute of Science, Faculty of Mathematics and Computer Science, Rehovot, Israel","institution_ids":["https://openalex.org/I53964585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035485534","display_name":"Benjamin Sach","orcid":"https://orcid.org/0000-0001-8360-9345"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benjamin Sach","raw_affiliation_strings":["University of Bristol, Department of Computer Science, Merchant Venturer's Building, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Bristol, Department of Computer Science, Merchant Venturer's Building, United Kingdom","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026696226","display_name":"Hjalte Wedel Vildh\u00f8j","orcid":null},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Hjalte Wedel Vildh\u00f8j","raw_affiliation_strings":["Technical University of Denmark, DTU Compute, Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark, DTU Compute, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5083100766"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":2.217,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90614959,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"12","issue":"3","first_page":"1","last_page":"19"},"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":0.9865999817848206,"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/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/search-engine-indexing","display_name":"Search engine indexing","score":0.7051296830177307},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6004670858383179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5238276124000549},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3784831166267395},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3542681336402893},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3303813338279724},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3222576677799225}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7051296830177307},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6004670858383179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5238276124000549},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3784831166267395},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3542681336402893},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3303813338279724},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3222576677799225},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2836166","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2836166","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"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 Transactions on Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.4422","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.4422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hwv.dk/pdfs/sparsetextindexinginsmallspace.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/820ab6bf-15a4-4dc7-984d-757deb3d37dd","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/820ab6bf-15a4-4dc7-984d-757deb3d37dd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bille , P , Fischer , J , G\u00f8rtz , I L , Kopelowitz , T , Sach , B & Vildh\u00f8j , H W 2016 , ' Sparse Text Indexing in Small Space ' , A C M Transactions on Algorithms , vol. 12 , no. 3 , 39 , pp. 1-19 . https://doi.org/10.1145/2836166","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/820ab6bf-15a4-4dc7-984d-757deb3d37dd","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/820ab6bf-15a4-4dc7-984d-757deb3d37dd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bille , P , Fischer , J , G\u00f8rtz , I L , Kopelowitz , T , Sach , B & Vildh\u00f8j , H W 2016 , ' Sparse Text Indexing in Small Space ' , A C M Transactions on Algorithms , vol. 12 , no. 3 , 39 , pp. 1-19 . https://doi.org/10.1145/2836166","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1489909987","https://openalex.org/W1502292638","https://openalex.org/W1505606212","https://openalex.org/W1548907175","https://openalex.org/W1554611468","https://openalex.org/W1605040544","https://openalex.org/W1972418517","https://openalex.org/W2000484009","https://openalex.org/W2034955722","https://openalex.org/W2035314514","https://openalex.org/W2045266738","https://openalex.org/W2049652268","https://openalex.org/W2076458424","https://openalex.org/W2078042165","https://openalex.org/W2090021115","https://openalex.org/W2106946062","https://openalex.org/W2141389982","https://openalex.org/W2155512447","https://openalex.org/W2158874082","https://openalex.org/W2159613260","https://openalex.org/W2160247847","https://openalex.org/W2186150488","https://openalex.org/W2273956042","https://openalex.org/W2434820933","https://openalex.org/W2533248932","https://openalex.org/W2561675875","https://openalex.org/W2950802534"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2188505374","https://openalex.org/W1558342070"],"abstract_inverted_index":{"In":[0,100],"this":[1,101,171],"work,":[2],"we":[3,141,248],"present":[4],"efficient":[5],"algorithms":[6],"for":[7,19,54,86,240],"constructing":[8,55],"sparse":[9,12,16,56,121,263],"suffix":[10,13,57,122],"trees,":[11],"arrays,":[14],"and":[15,193,216,237,276],"position":[17,264],"heaps":[18,265],"b":[20,35,62,92,135,151,165,213,227,271,273,279],"arbitrary":[21],"positions":[22],"of":[23,27,38,49,72,110,158,254],"a":[24,143,185,204],"text":[25],"T":[26,98,159],"length":[28],"n":[29,132,269],"while":[30],"using":[31,161],"only":[32,85,162],"O":[33,60,130,163,211,229,267,277],"(":[34,61,131,164,212,268,278],")":[36,52,63,136,166,214,274,280],"words":[37],"space":[39,64,182,215,235],"during":[40],"the":[41,46,70,87,91,108,111,120,195,219,241,252],"construction.":[42],"Attempts":[43],"at":[44,251],"breaking":[45],"na\u00efve":[47],"bound":[48],"\u03a9(":[50],"nb":[51],"time":[53,221,239,275],"trees":[58],"in":[59,75,89,97,129,176,180,218,266],"can":[65,126],"be":[66,127],"traced":[67],"back":[68],"to":[69,117,148,261],"origins":[71],"string":[73],"indexing":[74],"1968.":[76],"First":[77],"results":[78],"were":[79,94],"not":[80],"obtained":[81],"until":[82],"1996,":[83],"but":[84],"case":[88],"which":[90,181,208],"suffixes":[93,157],"evenly":[95],"spaced":[96],".":[99],"article,":[102],"there":[103],"is":[104,116,184,190,259],"no":[105],"constraint":[106],"on":[107,156],"locations":[109],"suffixes.":[112],"Our":[113,187],"main":[114],"contribution":[115],"show":[118,249],"that":[119,145,170],"tree":[123,197],"(and":[124],"array)":[125],"constructed":[128],"log":[133,272],"2":[134],"time.":[137],"To":[138],"achieve":[139],"this,":[140],"develop":[142],"technique":[144,172],"allows":[146],"one":[147],"efficiently":[149],"answer":[150],"longest":[152],"common":[153],"prefix":[154],"queries":[155],",":[160],"space.":[167,281],"We":[168,201],"expect":[169],"will":[173],"prove":[174],"useful":[175],"many":[177],"other":[178],"applications":[179],"usage":[183,236],"concern.":[186],"first":[188],"solution":[189],"Monte":[191,242],"Carlo,":[192],"outputs":[194],"correct":[196],"with":[198,223],"high":[199,224],"probability.":[200],"then":[202],"give":[203],"Las":[205],"Vegas":[206],"algorithm,":[207],"also":[209],"uses":[210],"runs":[217],"same":[220],"bounds":[222],"probability":[225],"when":[226],"=":[228],"(\u221a":[230],"n).":[231],"Additional":[232],"trade-offs":[233],"between":[234],"construction":[238],"Carlo":[243],"algorithm":[244],"are":[245],"given.":[246],"Finally,":[247],"that,":[250],"expense":[253],"slower":[255],"pattern":[256],"queries,":[257],"it":[258],"possible":[260],"construct":[262],"+":[270]},"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":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}