{"id":"https://openalex.org/W2017110500","doi":"https://doi.org/10.1145/2682862.2682866","title":"Blended Dictionaries for Reduced-Memory Lempel-Ziv Corpus Compression","display_name":"Blended Dictionaries for Reduced-Memory Lempel-Ziv Corpus Compression","publication_year":2014,"publication_date":"2014-11-17","ids":{"openalex":"https://openalex.org/W2017110500","doi":"https://doi.org/10.1145/2682862.2682866","mag":"2017110500"},"language":"en","primary_location":{"id":"doi:10.1145/2682862.2682866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2682862.2682866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Australasian Document Computing Symposium","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/A5086493023","display_name":"Jiancong Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Jiancong Tong","raw_affiliation_strings":["College of Computer and Control Engineering, Nankai University, China and Department of Computing and Information Systems, The University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer and Control Engineering, Nankai University, China and Department of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087794199","display_name":"Anthony Wirth","orcid":"https://orcid.org/0000-0003-3746-6704"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anthony Wirth","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Australia","Department of Computing and Information Systems, the University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Department of Computing and Information Systems, the University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Australia","Department of Computing and Information Systems, the University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Department of Computing and Information Systems, the University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08998838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"116"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.939300000667572,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9138000011444092,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/uncompressed-video","display_name":"Uncompressed video","score":0.8345769643783569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805609107017517},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.7720152139663696},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6391751766204834},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.6369114518165588},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.6187907457351685},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6168562769889832},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5868935585021973},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4479420483112335},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4434090852737427},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3941959738731384},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3583502173423767},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.2787381708621979},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.21965479850769043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12723317742347717},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10609516501426697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09700742363929749},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06888720393180847}],"concepts":[{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.8345769643783569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805609107017517},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.7720152139663696},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6391751766204834},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.6369114518165588},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.6187907457351685},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6168562769889832},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5868935585021973},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4479420483112335},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4434090852737427},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3941959738731384},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3583502173423767},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.2787381708621979},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.21965479850769043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12723317742347717},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10609516501426697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09700742363929749},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06888720393180847},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2682862.2682866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2682862.2682866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Australasian Document Computing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G173170502","display_name":"Efficient Synchronisation of Large Repositories","funder_award_id":"DP1093665","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1537803653","https://openalex.org/W1537923221","https://openalex.org/W1962019683","https://openalex.org/W1965672806","https://openalex.org/W2046038806","https://openalex.org/W2075576453","https://openalex.org/W2088386938","https://openalex.org/W2126129461"],"related_works":["https://openalex.org/W2576782855","https://openalex.org/W2359436045","https://openalex.org/W153119118","https://openalex.org/W2143531254","https://openalex.org/W2608759984","https://openalex.org/W363060408","https://openalex.org/W2003608043","https://openalex.org/W2055795184","https://openalex.org/W2123393931","https://openalex.org/W2295072202"],"abstract_inverted_index":{"Relative":[0],"Lempel-Ziv":[1],"(RLZ)":[2],"compression":[3,11,19,97,158],"has":[4],"been":[5],"shown":[6],"to":[7],"be":[8,46],"effective":[9],"for":[10,91,98,128,140],"of":[12,26,66,76,85,124,138,145],"large":[13,34],"text":[14],"repositories.":[15],"It":[16],"provides":[17,106],"high":[18,157],"ratios":[20],"with":[21,96,131],"extremely":[22],"fast":[23],"atomic":[24],"decompression":[25,51,132,162],"individual":[27,78],"documents.":[28],"However,":[29],"it":[30],"depends":[31],"on":[32],"a":[33,41,107,136],"in-memory":[35],"dictionary,":[36],"which":[37],"is":[38,155,159,164],"implemented":[39],"as":[40],"contiguous":[42],"string":[43],"that":[44,104],"must":[45],"accessed":[47,93],"randomly":[48],"during":[49],"the":[50,64,67,74,86,99,121,142],"process.":[52],"In":[53],"this":[54,129],"paper":[55],"we":[56,82],"explore":[57],"how":[58],"compressed":[59,125],"suffix":[60,70,126],"arrays":[61,71,127,148],"might":[62],"reduce":[63],"size":[65],"dictionary.":[68],"These":[69],"drastically":[72],"increase":[73],"cost":[75],"accessing":[77],"characters,":[79],"however,":[80],"so":[81],"propose":[83],"splitting":[84,105],"dictionary:":[87],"an":[88,150],"uncompressed":[89],"structure":[90],"frequently":[92],"dictionary":[94],"elements,":[95],"remainder.":[100],"Our":[101],"results":[102],"show":[103],"smoothly":[108],"tuneable":[109],"trade-off":[110],"between":[111],"access":[112],"time":[113,133],"and":[114,161],"memory":[115,154],"requirements,":[116],"but":[117],"does":[118],"not":[119],"overcome":[120],"inherent":[122],"limitations":[123],"application,":[130],"growing":[134],"by":[135],"factor":[137],"10":[139],"even":[141],"best":[143],"combination":[144],"parameters.":[146],"Suffix":[147],"comprise":[149],"attractive":[151],"option":[152],"where":[153],"limited,":[156],"paramount,":[160],"speed":[163],"unimportant.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
