{"id":"https://openalex.org/W1965672806","doi":"https://doi.org/10.1145/2009916.2010087","title":"Sample selection for dictionary-based corpus compression","display_name":"Sample selection for dictionary-based corpus compression","publication_year":2011,"publication_date":"2011-07-24","ids":{"openalex":"https://openalex.org/W1965672806","doi":"https://doi.org/10.1145/2009916.2010087","mag":"1965672806"},"language":"en","primary_location":{"id":"doi:10.1145/2009916.2010087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and 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/A5012026692","display_name":"Christopher Hoobin","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christopher Hoobin","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021097696","display_name":"Simon J. Puglisi","orcid":"https://orcid.org/0000-0001-7668-7636"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Simon Puglisi","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"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":["University of Melbourne, Melbourne, Australia","University of Melbourne, Melbourne, Australia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia,","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3489,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80110578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1137","last_page":"1138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8390771746635437},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.8302817940711975},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5979117155075073},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5838620066642761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5695185661315918},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5411635041236877},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5201228857040405},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4781376123428345},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4656330645084381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4642157554626465},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.45829614996910095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35182610154151917},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34874606132507324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07644805312156677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390771746635437},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.8302817940711975},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5979117155075073},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5838620066642761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5695185661315918},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5411635041236877},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5201228857040405},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4781376123428345},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4656330645084381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4642157554626465},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.45829614996910095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35182610154151917},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34874606132507324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07644805312156677},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"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/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/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2009916.2010087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1970765735","https://openalex.org/W1981420413","https://openalex.org/W2135494327","https://openalex.org/W2137661542","https://openalex.org/W2160484851","https://openalex.org/W2621280964"],"related_works":["https://openalex.org/W1512321724","https://openalex.org/W4231317009","https://openalex.org/W2367696392","https://openalex.org/W4383723869","https://openalex.org/W4293703255","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W1723410974"],"abstract_inverted_index":{"Compression":[0],"of":[1,44,47,66,82,104,137],"large":[2],"text":[3,56],"corpora":[4],"has":[5],"the":[6,31,48,55,92,138],"potential":[7],"to":[8,64,114],"drastically":[9],"reduce":[10],"both":[11],"storage":[12],"requirements":[13],"and":[14,29,62],"per-document":[15],"access":[16,148],"costs.":[17],"Adaptive":[18],"methods":[19,34],"used":[20,86,113],"for":[21,26],"general-purpose":[22],"compression":[23,98,146],"are":[24,52,85],"ineffective":[25],"this":[27],"application,":[28],"historically":[30],"most":[32],"successful":[33],"have":[35,73],"been":[36],"based":[37],"on":[38,54,145],"word-based":[39],"dictionaries,":[40],"which":[41,79,91],"allow":[42],"use":[43],"global":[45],"properties":[46],"text.":[49],"However,":[50],"these":[51],"dependent":[53],"complying":[57],"with":[58,141],"assumptions":[59],"about":[60],"content":[61],"lead":[63],"dictionaries":[65],"unpredictable":[67],"size.":[68],"In":[69],"recent":[70],"work":[71],"we":[72,107],"described":[74],"an":[75],"LZ-like":[76],"approach":[77],"in":[78,117],"sampled":[80,119],"blocks":[81],"a":[83,88],"corpus":[84,94],"as":[87,100],"dictionary":[89,125],"against":[90],"complete":[93],"is":[95],"compressed,":[96],"giving":[97],"twice":[99],"effective":[101],"than":[102,135],"that":[103,124],"zlib.":[105],"Here":[106],"explore":[108],"how":[109],"pre-processing":[110],"can":[111,127],"be":[112,128],"eliminate":[115],"redundancy":[116],"our":[118],"dictionary.":[120],"Our":[121],"experiments":[122],"show":[123],"size":[126],"reduced":[129],"by":[130],"50%":[131],"or":[132,147],"more":[133],"(less":[134],"0.1%":[136],"collection":[139],"size)":[140],"no":[142],"significant":[143],"effect":[144],"speed.":[149]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}