{"id":"https://openalex.org/W2075576453","doi":"https://doi.org/10.14778/2078331.2078341","title":"Relative Lempel-Ziv factorization for efficient storage and retrieval of web collections","display_name":"Relative Lempel-Ziv factorization for efficient storage and retrieval of web collections","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2075576453","doi":"https://doi.org/10.14778/2078331.2078341","mag":"2075576453"},"language":"en","primary_location":{"id":"doi:10.14778/2078331.2078341","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2078331.2078341","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","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":["School of Computer Science and Information Technology, RMIT University","School of Computer Science and Information Technology | RMIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT University","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology | RMIT University","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/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"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","GB"],"is_corresponding":false,"raw_author_name":"Simon J. Puglisi","raw_affiliation_strings":["School of Computer Science and Information Technology, RMIT University and King's College London","School of Computer Science and Information Technology, RMIT University and King's College London#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT University and King's College London","institution_ids":["https://openalex.org/I183935753","https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT University and King's College London#TAB#","institution_ids":["https://openalex.org/I183935753"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1112,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94030415,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"3","first_page":"265","last_page":"273"},"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":0.9955000281333923,"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":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8253330588340759},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.7617967128753662},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6554659008979797},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.586529552936554},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5692099332809448},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5068796277046204},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.48978543281555176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48954400420188904},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4777059555053711},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.43359848856925964},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4282761216163635},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35631346702575684},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3433619439601898},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3308175802230835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3069446086883545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1960081160068512},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1283782422542572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08324530720710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253330588340759},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.7617967128753662},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6554659008979797},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.586529552936554},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5692099332809448},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5068796277046204},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.48978543281555176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48954400420188904},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4777059555053711},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.43359848856925964},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4282761216163635},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35631346702575684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3433619439601898},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3308175802230835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3069446086883545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1960081160068512},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1283782422542572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08324530720710754},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2078331.2078341","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2078331.2078341","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1501322403","https://openalex.org/W1509384855","https://openalex.org/W1532325895","https://openalex.org/W1537803653","https://openalex.org/W1641949698","https://openalex.org/W1858013062","https://openalex.org/W1965672806","https://openalex.org/W1970765735","https://openalex.org/W1971520389","https://openalex.org/W1971849009","https://openalex.org/W1976118356","https://openalex.org/W1976149088","https://openalex.org/W1981420413","https://openalex.org/W2013849299","https://openalex.org/W2022292926","https://openalex.org/W2028009320","https://openalex.org/W2028347876","https://openalex.org/W2031302834","https://openalex.org/W2036407715","https://openalex.org/W2038807029","https://openalex.org/W2053003009","https://openalex.org/W2060108852","https://openalex.org/W2063841356","https://openalex.org/W2069906566","https://openalex.org/W2070641109","https://openalex.org/W2074281556","https://openalex.org/W2081893756","https://openalex.org/W2107745473","https://openalex.org/W2110764329","https://openalex.org/W2122962290","https://openalex.org/W2135494327","https://openalex.org/W2137339254","https://openalex.org/W2137661542","https://openalex.org/W2140453381","https://openalex.org/W2148212498","https://openalex.org/W2151637286","https://openalex.org/W2158874082","https://openalex.org/W2160484851","https://openalex.org/W2263798363","https://openalex.org/W2621280964","https://openalex.org/W4213009331","https://openalex.org/W6648424669","https://openalex.org/W6681966102"],"related_works":["https://openalex.org/W3047599943","https://openalex.org/W4383723869","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W3007688875","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W1723410974","https://openalex.org/W3209669196","https://openalex.org/W2110517301"],"abstract_inverted_index":{"Compression":[0],"techniques":[1],"that":[2,76,114],"support":[3],"fast":[4,78],"random":[5,79],"access":[6,36],"are":[7],"a":[8,28,38,45,68,83,93,96,116],"core":[9],"component":[10],"of":[11,44,49,86,99,102,122],"any":[12],"information":[13],"system.":[14],"Current":[15],"state-of-the-art":[16],"methods":[17],"group":[18],"documents":[19],"into":[20],"fixed-sized":[21],"blocks":[22],"and":[23,59,89,134],"compress":[24],"each":[25],"block":[26,50],"with":[27],"general-purpose":[29],"adaptive":[30],"algorithm":[31,127],"such":[32],"as":[33,92,118,120],"gzip.":[34],"Random":[35],"to":[37,106],"specific":[39],"document":[40,60,74],"then":[41],"requires":[42],"decompression":[43],"block.":[46],"The":[47],"choice":[48],"size":[51],"is":[52,128],"critical:":[53],"it":[54,91],"trades":[55],"between":[56],"compression":[57,70],"effectiveness":[58],"retrieval":[61],"times.":[62],"In":[63],"this":[64],"paper":[65],"we":[66],"present":[67],"scalable":[69],"method":[71],"for":[72],"large":[73,112],"collections":[75],"allows":[77],"access.":[80],"We":[81,109],"build":[82],"representative":[84],"sample":[85],"the":[87,100,103,107,123],"collection":[88,124],"use":[90],"dictionary":[94,117],"in":[95,135],"LZ77-like":[97],"encoding":[98],"rest":[101],"collection,":[104],"relative":[105],"dictionary.":[108],"demonstrate":[110],"on":[111],"collections,":[113],"using":[115],"small":[119],"0.1%":[121],"size,":[125],"our":[126],"dramatically":[129],"faster":[130],"than":[131],"previous":[132],"methods,":[133],"general":[136],"gives":[137],"much":[138],"better":[139],"compression.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}