{"id":"https://openalex.org/W1553071595","doi":"https://doi.org/10.3233/fi-2011-565","title":"Self-Indexed Grammar-Based Compression","display_name":"Self-Indexed Grammar-Based Compression","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W1553071595","doi":"https://doi.org/10.3233/fi-2011-565","mag":"1553071595"},"language":"en","primary_location":{"id":"doi:10.3233/fi-2011-565","is_oa":false,"landing_page_url":"https://doi.org/10.3233/fi-2011-565","pdf_url":null,"source":{"id":"https://openalex.org/S39012697","display_name":"Fundamenta Informaticae","issn_l":"0169-2968","issn":["0169-2968","1875-8681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fundamenta Informaticae","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/A5091203911","display_name":"Francisco Claude","orcid":null},"institutions":[{"id":"https://openalex.org/I122879082","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29","country_code":"CA","type":"government","lineage":["https://openalex.org/I122879082"]},{"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":true,"raw_author_name":"Francisco Claude","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo, Canada. fclaude@cs.uwaterloo.ca","(Correspd.) (Funded in part by NSERC Canada, Go-Bell Scholarships program and David R. Cheriton Graduate Scholarships program.) David R. Cheriton School of Computer Science, University of Waterloo "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Canada. fclaude@cs.uwaterloo.ca","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(Correspd.) (Funded in part by NSERC Canada, Go-Bell Scholarships program and David R. Cheriton Graduate Scholarships program.) David R. Cheriton School of Computer Science, University of Waterloo ","institution_ids":["https://openalex.org/I122879082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080743153","display_name":"Gonzalo Navarro","orcid":"https://orcid.org/0000-0002-2286-741X"},"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":"Gonzalo Navarro","raw_affiliation_strings":["Department of Computer Science, University of Chile, Chile. gnavarro@dcc.uchile.cl","(Funded in part by Millennium Institute on Cell Dynamics and Biotechnology (ICDB), Grant ICM P05-001-F, Mideplan, Chile) Department of Computer Science, University of Chile, Chile. gnavarro@dcc.uc ...#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chile, Chile. gnavarro@dcc.uchile.cl","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"(Funded in part by Millennium Institute on Cell Dynamics and Biotechnology (ICDB), Grant ICM P05-001-F, Mideplan, Chile) Department of Computer Science, University of Chile, Chile. gnavarro@dcc.uc ...#TAB#","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091203911"],"corresponding_institution_ids":["https://openalex.org/I122879082","https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":16.2684,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.99101746,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"111","issue":"3","first_page":"313","last_page":"337"},"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/T12029","display_name":"DNA and Biological Computing","score":0.9866999983787537,"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"}},{"id":"https://openalex.org/T11567","display_name":"semigroups and automata theory","score":0.973800003528595,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.5731686949729919},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5519688129425049},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.484391987323761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4489240348339081},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2514514625072479},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0844569206237793},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05429220199584961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5731686949729919},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5519688129425049},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.484391987323761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4489240348339081},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2514514625072479},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0844569206237793},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05429220199584961},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3233/fi-2011-565","is_oa":false,"landing_page_url":"https://doi.org/10.3233/fi-2011-565","pdf_url":null,"source":{"id":"https://openalex.org/S39012697","display_name":"Fundamenta Informaticae","issn_l":"0169-2968","issn":["0169-2968","1875-8681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fundamenta Informaticae","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.123","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/%7Egnavarro/algoritmos/ps/fi10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.9070","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.9070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/%7Egnavarro/ps/fi10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.8679","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.8679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/~gnavarro/algoritmos/ps/fi10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W181668213","https://openalex.org/W1484484268","https://openalex.org/W1489909987","https://openalex.org/W1509727978","https://openalex.org/W1548111976","https://openalex.org/W1565650557","https://openalex.org/W1577336816","https://openalex.org/W1603565140","https://openalex.org/W1730684757","https://openalex.org/W1831273253","https://openalex.org/W1971849009","https://openalex.org/W1973608346","https://openalex.org/W1974785036","https://openalex.org/W1976149088","https://openalex.org/W1979271813","https://openalex.org/W1985108724","https://openalex.org/W1985174631","https://openalex.org/W2012016911","https://openalex.org/W2013291893","https://openalex.org/W2018403675","https://openalex.org/W2022126655","https://openalex.org/W2024147613","https://openalex.org/W2027244654","https://openalex.org/W2041824945","https://openalex.org/W2044014345","https://openalex.org/W2046038806","https://openalex.org/W2073921136","https://openalex.org/W2088386938","https://openalex.org/W2097589086","https://openalex.org/W2107082304","https://openalex.org/W2107745473","https://openalex.org/W2111487449","https://openalex.org/W2113004376","https://openalex.org/W2122962290","https://openalex.org/W2130080588","https://openalex.org/W2130564474","https://openalex.org/W2130956967","https://openalex.org/W2132809979","https://openalex.org/W2134696992","https://openalex.org/W2138947530","https://openalex.org/W2143024569","https://openalex.org/W2147217460","https://openalex.org/W2148113067","https://openalex.org/W2152486057","https://openalex.org/W2155512447","https://openalex.org/W2157821460","https://openalex.org/W2158874082","https://openalex.org/W2159647614","https://openalex.org/W2160748429","https://openalex.org/W2295740354","https://openalex.org/W2602771387","https://openalex.org/W2646645486","https://openalex.org/W3042165818","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Self-indexes":[0],"aim":[1],"at":[2],"representing":[3],"text":[4,35,78,112],"collections":[5,36],"in":[6,39,117,135],"a":[7,63,77,129,171,190,196,208,220],"compressed":[8],"format":[9],"that":[10,37,94,175,216],"allows":[11],"extracting":[12],"arbitrary":[13],"portions":[14],"and":[15,124,184,224,229],"also":[16],"offers":[17],"indexed":[18],"searching":[19],"on":[20,59],"the":[21,30,53,148,151,155],"collection.":[22],"Current":[23],"self-indexes":[24],"are":[25],"unable":[26],"of":[27,32,67,73,85,114,128,132,150,154,173,193,210,222],"fully":[28],"exploiting":[29],"redundancy":[31],"highly":[33],"repetitive":[34],"arise":[38],"several":[40],"applications.":[41],"Grammar-based":[42],"compression":[43],"is":[44,147],"well":[45],"suited":[46],"to":[47,213,219],"exploit":[48],"such":[49,226],"repetitiveness.":[50],"We":[51],"introduce":[52,169],"first":[54],"grammar-based":[55],"self-index.":[56],"It":[57,109],"builds":[58],"Straight-Line":[60],"Programs":[61],"(SLPs),":[62],"rather":[64],"general":[65],"kind":[66],"context-free":[68],"grammars.":[69],"If":[70],"an":[71,82],"SLP":[72],"n":[74,91,104],"rules":[75],"represents":[76],"T[1,":[79],"u],":[80],"then":[81],"SLP-compressed":[83],"representation":[84,160,172,197],"T":[86,218],"requires":[87],"2n":[88,177],"log":[89,101,105,122,143,178],"2":[90,106,179],"bits.":[92,108],"For":[93],"same":[95],"SLP,":[96],"our":[97,211],"self-index":[98,212],"takes":[99,176],"O(n":[100],"n)":[102],"+":[103,120,138,140,181],"u":[107],"extracts":[110],"any":[111],"substring":[113],"length":[115,133],"m":[116,134],"time":[118,136],"O((m":[119],"h)":[121,139],"n),":[123,144],"finds":[125],"occ":[126],"occurrences":[127],"pattern":[130],"string":[131],"O((m(m":[137],"h":[141,146],"occ)":[142],"where":[145],"height":[149],"parse":[152],"tree":[153],"SLP.":[156],"No":[157],"previous":[158],"grammar":[159,214],"had":[161],"achieved":[162],"o(n)":[163],"search":[164],"time.":[165],"As":[166],"byproducts":[167],"we":[168],"(i)":[170],"SLPs":[174],"n(1":[180],"o(1))":[182],"bits":[183],"efficiently":[185],"supports":[186],"more":[187],"operations":[188],"than":[189],"plain":[191],"array":[192],"rules;":[194],"(ii)":[195],"for":[198],"binary":[199],"relations":[200],"with":[201],"labels":[202],"supporting":[203],"various":[204],"extended":[205],"queries;":[206],"(iii)":[207],"generalization":[209],"compressors":[215],"reduce":[217],"sequence":[221],"terminals":[223],"nonterminals,":[225],"as":[227],"Re-Pair":[228],"LZ78.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":13}],"updated_date":"2026-05-02T06:04:40.494371","created_date":"2025-10-10T00:00:00"}