{"id":"https://openalex.org/W1560697993","doi":"https://doi.org/10.1109/dcc.2003.1194067","title":"A dictionary-based multi-corpora text compression system","display_name":"A dictionary-based multi-corpora text compression system","publication_year":2003,"publication_date":"2003-11-04","ids":{"openalex":"https://openalex.org/W1560697993","doi":"https://doi.org/10.1109/dcc.2003.1194067","mag":"1560697993"},"language":"en","primary_location":{"id":"doi:10.1109/dcc.2003.1194067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc.2003.1194067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Compression Conference, 2003. Proceedings. DCC 2003","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://stars.library.ucf.edu/scopus2000/1958","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100810511","display_name":"Welfeng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Welfeng Sun","raw_affiliation_strings":["Computer Science Department, University of Central Florida, Orlando, FL, USA","[Dept. of Comput. Sci., Central Florida Univ., Orlando, FL, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Central Florida Univ., Orlando, FL, USA]","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103883353","display_name":"Nan Zhang","orcid":"https://orcid.org/0009-0001-1836-7332"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["Computer Science Department, University of Central Florida, Orlando, FL, USA","[Dept. of Comput. Sci., Central Florida Univ., Orlando, FL, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Central Florida Univ., Orlando, FL, USA]","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109107792","display_name":"Amar Mukherjee","orcid":"https://orcid.org/0009-0003-7658-6132"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Mukherjee","raw_affiliation_strings":["Computer Science Department, University of Central Florida, Orlando, FL, USA","[Dept. of Comput. Sci., Central Florida Univ., Orlando, FL, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Central Florida Univ., Orlando, FL, USA]","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100810511"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":1.4045,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.8412506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"448","last_page":"448"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9611999988555908,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9488999843597412,"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/computer-science","display_name":"Computer science","score":0.8275717496871948},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.8114486336708069},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6323373317718506},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5882482528686523},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.518101155757904},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.46788424253463745},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.46724963188171387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45825445652008057},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44655436277389526},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4142211377620697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3935491144657135},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.33914288878440857},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33739838004112244},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.12136858701705933},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11468493938446045},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07988405227661133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275717496871948},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.8114486336708069},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6323373317718506},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5882482528686523},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.518101155757904},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.46788424253463745},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.46724963188171387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45825445652008057},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44655436277389526},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4142211377620697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935491144657135},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.33914288878440857},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33739838004112244},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.12136858701705933},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11468493938446045},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07988405227661133},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","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},{"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/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/dcc.2003.1194067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc.2003.1194067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Compression Conference, 2003. Proceedings. DCC 2003","raw_type":"proceedings-article"},{"id":"pmh:oai:stars.library.ucf.edu:scopus2000-2957","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2000/1958","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2000s","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.8425","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.8425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vlsi.cs.ucf.edu/datacomp/papers/dcc2003sun.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:stars.library.ucf.edu:scopus2000-2957","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2000/1958","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2000s","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1498488333","https://openalex.org/W1499671174","https://openalex.org/W1571468614","https://openalex.org/W1696088198","https://openalex.org/W1828656815","https://openalex.org/W1869490816","https://openalex.org/W1875619160","https://openalex.org/W1924135377","https://openalex.org/W1938301739","https://openalex.org/W2000484009","https://openalex.org/W2006091169","https://openalex.org/W2135771747","https://openalex.org/W2161488606"],"related_works":["https://openalex.org/W2521595930","https://openalex.org/W4313046148","https://openalex.org/W2751842002","https://openalex.org/W2161981399","https://openalex.org/W3180760233","https://openalex.org/W2096442341","https://openalex.org/W1680283075","https://openalex.org/W2207317090","https://openalex.org/W2088378984","https://openalex.org/W3080614128"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"StarZip,":[4],"a":[5,47,65,81,123,130,136,160],"multi-copora":[6],"text":[7,69,116],"compression":[8,26,49,178,194,223],"system,":[9],"was":[10,42],"introduced":[11],"together":[12],"with":[13,80,135,200],"its":[14],"transform":[15,90,133,153,169,189],"engine":[16],"StarNT.":[17],"One":[18],"of":[19,23,83,93,113,149,196,227,229],"the":[20,24,54,94,99,111,114,143,152,163,168,176],"key":[21],"features":[22],"StarZip":[25,217],"system":[27],"is":[28,64,74,120,165,203],"to":[29,37,75,122,186],"develop":[30,38],"domain":[31],"specific":[32],"dictionaries":[33],"and":[34,61,102,193,208,236],"provide":[35],"tools":[36],"such":[39],"dictionaries.":[40],"StarNT":[41,63,140],"utilized":[43],"because":[44],"it":[45],"achieves":[46],"superior":[48],"ratio":[50],"than":[51,86,205],"almost":[52],"all":[53],"other":[55],"recent":[56],"efforts":[57],"based":[58],"on":[59],"BWT":[60],"PPM.":[62],"dictionary-based":[66,188],"fast":[67,132],"lossless":[68],"transform.":[70],"The":[71,155,191],"main":[72],"idea":[73],"record":[76],"each":[77],"English":[78],"word":[79,100,161],"representation":[82],"no":[84],"more":[85],"three":[87],"symbols.":[88],"This":[89,126],"maintains":[91],"most":[92],"original":[95],"context":[96],"information":[97],"at":[98],"level":[101],"provides":[103,129],"an":[104,147,219],"\"artificial\"":[105],"strong":[106],"context.":[107],"It":[108],"ultimately":[109],"reduces":[110],"size":[112],"transformed":[115,144],"that,":[117],"in":[118,151,162,167,198,222],"turn,":[119],"provided":[121],"backend":[124],"compressor.":[125],"data":[127],"structure":[128],"very":[131],"encoding":[134],"low":[137],"storage":[138],"overhead.":[139],"also":[141],"treats":[142],"codewords":[145],"as":[146],"offset":[148],"words":[150],"dictionary.":[154],"time":[156,179],"complexity":[157,192],"for":[158],"searching":[159],"dictionary":[164],"achieved":[166,218],"decoder.":[170],"Experimental":[171],"results":[172],"have":[173,214],"shown":[174,215],"that":[175,216],"average":[177,220],"has":[180],"improved":[181],"by":[182],"orders":[183],"magnitude":[184],"compared":[185],"previous":[187],"LIPT.":[190],"performance":[195,224],"bzip2,":[197],"conjunction":[199],"this":[201],"transform,":[202],"better":[204],"both":[206],"gzip":[207],"PPMD.":[209,239],"Results":[210],"from":[211],"five":[212],"copora":[213],"improvement":[221],"(in":[225],"terms":[226],"BPC)":[228],"13%":[230],"over":[231,234,238],"bzip2-9,":[232],"19%":[233],"gzip-9,":[235],"10%":[237]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}