{"id":"https://openalex.org/W2012603689","doi":"https://doi.org/10.1145/76894.76896","title":"Modeling for text compression","display_name":"Modeling for text compression","publication_year":1989,"publication_date":"1989-12-01","ids":{"openalex":"https://openalex.org/W2012603689","doi":"https://doi.org/10.1145/76894.76896","mag":"2012603689"},"language":"en","primary_location":{"id":"doi:10.1145/76894.76896","doi":"https://doi.org/10.1145/76894.76896","is_oa":true,"landing_page_url":"https://doi.org/10.1145/76894.76896","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/76894.76896","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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 Computing Surveys","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/76894.76896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051736855","display_name":"Tim Bell","orcid":"https://orcid.org/0000-0002-0148-0857","observed_orcids":["https://orcid.org/0000-0002-0148-0857"]},"institutions":[{"id":"https://openalex.org/I185492890","display_name":"University of Canterbury","ror":"https://ror.org/03y7q9t39","country_code":"NZ","type":"education","lineage":["https://openalex.org/I185492890"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Timothy Bell","raw_affiliation_strings":["Univ. of Canterbury, Christchurch, New Zealand","University of Canterbury, Christchurch , New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Canterbury, Christchurch, New Zealand","institution_ids":["https://openalex.org/I185492890"]},{"raw_affiliation_string":"University of Canterbury, Christchurch , New Zealand","institution_ids":["https://openalex.org/I185492890"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045934263","display_name":"Ian H. Witten","orcid":"https://orcid.org/0000-0001-6428-8988","observed_orcids":["https://orcid.org/0000-0001-6428-8988"]},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ian H. Witten","raw_affiliation_strings":["Univ. of Calgary, Calgary, Alta., Canada","University of Calgary, Calgary Alta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Calgary, Calgary, Alta., Canada","institution_ids":["https://openalex.org/I168635309"]},{"raw_affiliation_string":"University of Calgary, Calgary Alta., Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104360602","display_name":"John G. Cleary","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"John G. Cleary","raw_affiliation_strings":["Univ. of Calgary, Calgary, Alta., Canada","University of Calgary, Calgary Alta., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Calgary, Calgary, Alta., Canada","institution_ids":["https://openalex.org/I168635309"]},{"raw_affiliation_string":"University of Calgary, Calgary Alta., Canada","institution_ids":["https://openalex.org/I168635309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9703,"has_fulltext":true,"cited_by_count":261,"citation_normalized_percentile":{"value":0.97892908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"21","issue":"4","first_page":"557","last_page":"591"},"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":0.0,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-compression","display_name":"text compression","score":0.996999979019165},{"id":"https://openalex.org/keywords/adaptive-modeling","display_name":"adaptive modeling","score":0.902999997138977},{"id":"https://openalex.org/keywords/context-modeling","display_name":"context modeling","score":0.3919999897480011},{"id":"https://openalex.org/keywords/density-estimation","display_name":"density estimation","score":0.35499998927116394},{"id":"https://openalex.org/keywords/dictionary-based-compression","display_name":"dictionary-based compression","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741451501846313},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6327321529388428},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6252055168151855},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5230023264884949},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.4918644428253174},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44139763712882996},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4344331622123718},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.431276798248291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40899717807769775},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3688487410545349},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.361880362033844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3378334641456604},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/76894.76896","doi":"https://doi.org/10.1145/76894.76896","is_oa":true,"landing_page_url":"https://doi.org/10.1145/76894.76896","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/76894.76896","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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 Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:ucalgary.scholaris.ca:1880/46173","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1880/46173","pdf_url":null,"source":{"id":"https://openalex.org/S4306402261","display_name":"Libraries and Cultural Resources (University of Calgary)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I168635309","host_organization_name":"University of Calgary","host_organization_lineage":["https://openalex.org/I168635309"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"unknown"},{"id":"doi:10.11575/prism/31168","doi":"https://doi.org/10.11575/prism/31168","is_oa":true,"landing_page_url":"https://doi.org/10.11575/prism/31168","pdf_url":null,"source":{"id":"https://openalex.org/S4306402261","display_name":"Libraries and Cultural Resources (University of Calgary)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I168635309","host_organization_name":"University of Calgary","host_organization_lineage":["https://openalex.org/I168635309"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.1145/76894.76896","doi":"https://doi.org/10.1145/76894.76896","is_oa":true,"landing_page_url":"https://doi.org/10.1145/76894.76896","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/76894.76896","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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 Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2012603689.pdf","grobid_xml":"https://content.openalex.org/works/W2012603689.grobid-xml"},"referenced_works_count":110,"referenced_works":["https://openalex.org/W185091403","https://openalex.org/W1484254303","https://openalex.org/W1510043860","https://openalex.org/W1513153538","https://openalex.org/W1519253855","https://openalex.org/W1520935423","https://openalex.org/W1547966682","https://openalex.org/W1575696892","https://openalex.org/W1974717499","https://openalex.org/W1975965284","https://openalex.org/W1985966121","https://openalex.org/W1990653637","https://openalex.org/W1995875735","https://openalex.org/W1997162174","https://openalex.org/W2001232605","https://openalex.org/W2002855154","https://openalex.org/W2003153196","https://openalex.org/W2009981574","https://openalex.org/W2013299585","https://openalex.org/W2017603160","https://openalex.org/W2017661493","https://openalex.org/W2022126655","https://openalex.org/W2022797591","https://openalex.org/W2026881511","https://openalex.org/W2027891831","https://openalex.org/W2029353114","https://openalex.org/W2031366154","https://openalex.org/W2033563072","https://openalex.org/W2033971168","https://openalex.org/W2036407715","https://openalex.org/W2037818726","https://openalex.org/W2037950039","https://openalex.org/W2038649859","https://openalex.org/W2041118088","https://openalex.org/W2042357346","https://openalex.org/W2046419776","https://openalex.org/W2046825849","https://openalex.org/W2047500929","https://openalex.org/W2050930003","https://openalex.org/W2053515226","https://openalex.org/W2056358764","https://openalex.org/W2056915456","https://openalex.org/W2060082998","https://openalex.org/W2060108852","https://openalex.org/W2060309068","https://openalex.org/W2061079066","https://openalex.org/W2062460902","https://openalex.org/W2064710146","https://openalex.org/W2066464728","https://openalex.org/W2070428720","https://openalex.org/W2077770566","https://openalex.org/W2079145130","https://openalex.org/W2082967074","https://openalex.org/W2085880494","https://openalex.org/W2086699924","https://openalex.org/W2087039252","https://openalex.org/W2090915139","https://openalex.org/W2091794796","https://openalex.org/W2091903496","https://openalex.org/W2092535964","https://openalex.org/W2093076589","https://openalex.org/W2094396384","https://openalex.org/W2097530618","https://openalex.org/W2100016822","https://openalex.org/W2105594594","https://openalex.org/W2105807716","https://openalex.org/W2107745473","https://openalex.org/W2107927941","https://openalex.org/W2117455376","https://openalex.org/W2117946854","https://openalex.org/W2119047110","https://openalex.org/W2120465215","https://openalex.org/W2122962290","https://openalex.org/W2128066268","https://openalex.org/W2128777897","https://openalex.org/W2129652681","https://openalex.org/W2134547831","https://openalex.org/W2134893012","https://openalex.org/W2137012911","https://openalex.org/W2138026948","https://openalex.org/W2144679335","https://openalex.org/W2151344646","https://openalex.org/W2152851525","https://openalex.org/W2154259526","https://openalex.org/W2155512447","https://openalex.org/W2161628678","https://openalex.org/W2165564574","https://openalex.org/W2166332856","https://openalex.org/W2171763016","https://openalex.org/W2171850596","https://openalex.org/W2284001759","https://openalex.org/W2292676262","https://openalex.org/W2295528854","https://openalex.org/W2318645193","https://openalex.org/W2603253565","https://openalex.org/W2752853835","https://openalex.org/W2752908210","https://openalex.org/W2911940095","https://openalex.org/W3198160809","https://openalex.org/W4254427705","https://openalex.org/W4285719527","https://openalex.org/W6607594530","https://openalex.org/W6632717440","https://openalex.org/W6634228472","https://openalex.org/W6648424669","https://openalex.org/W6649495502","https://openalex.org/W6674668859","https://openalex.org/W6681546935","https://openalex.org/W6744529318","https://openalex.org/W6959897281"],"related_works":["https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W3029188025","https://openalex.org/W2116404931","https://openalex.org/W2121572690","https://openalex.org/W1549771939","https://openalex.org/W4384392961"],"abstract_inverted_index":{"The":[0,18,64],"best":[1,36],"schemes":[2],"for":[3,51,57,86],"text":[4,42,61],"compression":[5,31,62],"use":[6,58],"large":[7],"models":[8],"to":[9,26,81],"help":[10],"them":[11],"predict":[12],"which":[13,74,93,103,116],"characters":[14,21,78,119],"will":[15],"come":[16],"next.":[17],"actual":[19],"next":[20,88],"are":[22,35,55,79,120],"coded":[23],"with":[24,141],"respect":[25],"the":[27,41,75,83,87,94,99,134],"prediction,":[28],"resulting":[29],"in":[30,59,73,92,115],"of":[32,118,130,144],"information.":[33],"Models":[34],"formed":[37],"adaptively,":[38],"based":[39],"on":[40,133],"seen":[43],"so":[44],"far.":[45],"This":[46],"paper":[47],"surveys":[48],"successful":[49],"strategies":[50,65],"adaptive":[52],"modeling":[53,106],"that":[54],"suitable":[56],"practical":[60],"systems.":[63],"fall":[66],"into":[67,124],"three":[68],"main":[69],"classes:":[70],"finite-context":[71,105],"modeling,":[72,91,114],"last":[76],"few":[77],"used":[80],"condition":[82],"probability":[84],"distribution":[85,95],"one;":[89],"finite-state":[90],"is":[96,138],"conditioned":[97],"by":[98,122],"current":[100],"state":[101],"(and":[102],"subsumes":[104],"as":[107],"an":[108,125,142],"important":[109],"special":[110],"case);":[111],"and":[112],"dictionary":[113],"strings":[117],"replaced":[121],"pointers":[123],"evolving":[126],"dictionary.":[127],"A":[128],"comparison":[129],"different":[131],"methods":[132],"same":[135],"sample":[136],"texts":[137],"included,":[139],"along":[140],"analysis":[143],"future":[145],"research":[146],"directions.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":8}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}