{"id":"https://openalex.org/W2126129461","doi":"https://doi.org/10.1145/2600428.2609576","title":"Principled dictionary pruning for low-memory corpus compression","display_name":"Principled dictionary pruning for low-memory corpus compression","publication_year":2014,"publication_date":"2014-07-03","ids":{"openalex":"https://openalex.org/W2126129461","doi":"https://doi.org/10.1145/2600428.2609576","mag":"2126129461"},"language":"en","primary_location":{"id":"doi:10.1145/2600428.2609576","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600428.2609576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval","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/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiancong Tong","raw_affiliation_strings":["Nankai University, Tianjin, China","Nankai University, Tianjin, China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China)","institution_ids":["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":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, 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":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, 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":1.2409,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81920228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"292"},"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":0.9889000058174133,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9822999835014343,"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/substring","display_name":"Substring","score":0.8284919261932373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8263847827911377},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5724942684173584},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5699363350868225},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5497395396232605},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4468626379966736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4361494183540344},{"id":"https://openalex.org/keywords/k-svd","display_name":"K-SVD","score":0.42840084433555603},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.42082899808883667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2523736357688904},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.16922909021377563},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.09085461497306824}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8284919261932373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263847827911377},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5724942684173584},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5699363350868225},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5497395396232605},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4468626379966736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361494183540344},{"id":"https://openalex.org/C154771677","wikidata":"https://www.wikidata.org/wiki/Q17098361","display_name":"K-SVD","level":3,"score":0.42840084433555603},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.42082899808883667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2523736357688904},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.16922909021377563},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.09085461497306824},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2600428.2609576","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2600428.2609576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2274309997","display_name":null,"funder_award_id":"NCET130301","funder_id":"https://openalex.org/F4320334924","funder_display_name":"Program for New Century Excellent Talents in University"},{"id":"https://openalex.org/G6987066815","display_name":"\u57fa\u4e8eGPU\u7684\u641c\u7d22\u5f15\u64ce\u6570\u636e\u7ec4\u7ec7\u548c\u5206\u5e03\u6280\u672f\u7814\u7a76","funder_award_id":"61373018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"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"},{"id":"https://openalex.org/F4320334924","display_name":"Program for New Century Excellent Talents in University","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W60779023","https://openalex.org/W110439420","https://openalex.org/W153132339","https://openalex.org/W202663801","https://openalex.org/W1483313504","https://openalex.org/W1492896593","https://openalex.org/W1532325895","https://openalex.org/W1660390307","https://openalex.org/W1858013062","https://openalex.org/W1965672806","https://openalex.org/W1970765735","https://openalex.org/W1972418517","https://openalex.org/W1974674140","https://openalex.org/W1976149088","https://openalex.org/W1978089967","https://openalex.org/W2018017294","https://openalex.org/W2022126655","https://openalex.org/W2028347876","https://openalex.org/W2050140640","https://openalex.org/W2063841356","https://openalex.org/W2073370301","https://openalex.org/W2075576453","https://openalex.org/W2087361130","https://openalex.org/W2088386938","https://openalex.org/W2096258819","https://openalex.org/W2099676315","https://openalex.org/W2107745473","https://openalex.org/W2110764329","https://openalex.org/W2132627996","https://openalex.org/W2135494327","https://openalex.org/W2137661542","https://openalex.org/W2138662031","https://openalex.org/W2138831039","https://openalex.org/W2147755199","https://openalex.org/W2148212498","https://openalex.org/W2160484851","https://openalex.org/W2263798363","https://openalex.org/W2583349018","https://openalex.org/W2621280964","https://openalex.org/W4251504464","https://openalex.org/W4285719527","https://openalex.org/W6602511761","https://openalex.org/W7033535967"],"related_works":["https://openalex.org/W3132814725","https://openalex.org/W4383723869","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W1723410974","https://openalex.org/W3007688875","https://openalex.org/W3209669196","https://openalex.org/W2766695209"],"abstract_inverted_index":{"Compression":[0],"of":[1,22,37,103,127,149,160,162],"collections,":[2],"such":[3],"as":[4,43],"text":[5,163],"databases,":[6],"can":[7],"both":[8],"reduce":[9],"space":[10],"consumption":[11],"and":[12,19,56,75,155],"increase":[13],"retrieval":[14],"efficiency,":[15],"through":[16],"better":[17,20],"caching":[18],"exploitation":[21],"the":[23,40,79,96,153,167],"memory":[24,142],"hierarchy.":[25],"A":[26],"promising":[27],"technique":[28],"is":[29,69,98,179],"relative":[30],"Lempel-Ziv":[31],"coding,":[32],"in":[33,47,113,152,175],"which":[34],"a":[35,44,70,82,124,137,141,158,180],"sample":[36],"material":[38],"from":[39],"collection":[41,139,164],"serves":[42],"static":[45],"dictionary;":[46],"previous":[48,89,184],"work,":[49],"this":[50],"method":[51],"demonstrated":[52],"extremely":[53],"fast":[54],"decoding":[55],"good":[57],"compression":[58,76,176],"ratios,":[59],"while":[60],"allowing":[61],"random":[62],"access":[63],"to":[64,171],"individual":[65],"items.":[66],"However,":[67],"there":[68],"trade-off":[71],"between":[72],"dictionary":[73,97,117,135,168],"size":[74,169],"ratio,":[77],"motivating":[78],"search":[80],"for":[81,136,147],"compact,":[83],"yet":[84],"similarly":[85],"effective,":[86],"dictionary.":[87],"In":[88],"work":[90],"it":[91,104],"was":[92],"observed":[93],"that,":[94],"since":[95],"generated":[99],"by":[100],"sampling,":[101],"some":[102],"(selected":[105],"substrings)":[106],"may":[107],"be":[108],"discarded":[109],"with":[110],"little":[111],"loss":[112,174],"compression.":[114],"Unfortunately,":[115],"simple":[116],"pruning":[118],"approaches":[119],"are":[120],"ineffective.":[121],"We":[122,144],"develop":[123],"formal":[125],"model":[126],"our":[128],"approach,":[129],"based":[130],"on":[131,157,183],"generating":[132],"an":[133],"optimal":[134],"given":[138],"within":[140],"bound.":[143],"generate":[145],"measures":[146],"identification":[148],"low-value":[150],"substrings":[151],"dictionary,":[154],"show":[156],"variety":[159],"sizes":[161],"that":[165],"halving":[166],"leads":[170],"only":[172],"marginal":[173],"ratio.":[177],"This":[178],"dramatic":[181],"improvement":[182],"approaches.":[185]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}