{"id":"https://openalex.org/W2888958910","doi":"https://doi.org/10.14778/3236187.3236203","title":"Efficient document analytics on compressed data","display_name":"Efficient document analytics on compressed data","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2888958910","doi":"https://doi.org/10.14778/3236187.3236203","mag":"2888958910"},"language":"en","primary_location":{"id":"doi:10.14778/3236187.3236203","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3236187.3236203","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/A5091139467","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0003-1983-7321"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Renmin University of China, MOE and Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, MOE and Tsinghua University, China","institution_ids":["https://openalex.org/I78988378","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050695684","display_name":"Onur Mutlu","orcid":"https://orcid.org/0000-0002-0075-2312"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Onur Mutlu","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguang Chen","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091139467"],"corresponding_institution_ids":["https://openalex.org/I78988378","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.3647,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.91307356,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":"11","first_page":"1522","last_page":"1535"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9979000091552734,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.993399977684021,"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":0.8285446763038635},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.7540640234947205},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.528688371181488},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.48293086886405945},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4515751898288727},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4431167542934418},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.43299758434295654},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41696983575820923},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41267046332359314},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3913336992263794},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3318323493003845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25583815574645996},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10843789577484131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285446763038635},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.7540640234947205},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.528688371181488},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.48293086886405945},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4515751898288727},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4431167542934418},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.43299758434295654},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41696983575820923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41267046332359314},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3913336992263794},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3318323493003845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25583815574645996},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10843789577484131},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3236187.3236203","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3236187.3236203","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W17864305","https://openalex.org/W78077100","https://openalex.org/W1547576067","https://openalex.org/W1550028225","https://openalex.org/W1610496399","https://openalex.org/W1982003698","https://openalex.org/W1983311025","https://openalex.org/W1988637082","https://openalex.org/W1994694191","https://openalex.org/W2001496424","https://openalex.org/W2031709923","https://openalex.org/W2041445031","https://openalex.org/W2049342105","https://openalex.org/W2054439442","https://openalex.org/W2059504991","https://openalex.org/W2070948110","https://openalex.org/W2074214454","https://openalex.org/W2093824812","https://openalex.org/W2095063920","https://openalex.org/W2104290389","https://openalex.org/W2107745473","https://openalex.org/W2108112890","https://openalex.org/W2136794719","https://openalex.org/W2152437528","https://openalex.org/W2155072926","https://openalex.org/W2159647614","https://openalex.org/W2161488606","https://openalex.org/W2170616854","https://openalex.org/W2244508245","https://openalex.org/W2250570571","https://openalex.org/W2467794313","https://openalex.org/W2477279521","https://openalex.org/W2489406233","https://openalex.org/W2566979091","https://openalex.org/W2625691739","https://openalex.org/W2743862488","https://openalex.org/W2890532380","https://openalex.org/W2891870102","https://openalex.org/W3003570873","https://openalex.org/W3161192096","https://openalex.org/W4246219036","https://openalex.org/W6600737987","https://openalex.org/W6607453207","https://openalex.org/W6636177537","https://openalex.org/W6640789038","https://openalex.org/W6675354045","https://openalex.org/W6687322159","https://openalex.org/W6691174005","https://openalex.org/W6736575291","https://openalex.org/W7029321148"],"related_works":["https://openalex.org/W2003932708","https://openalex.org/W2138102289","https://openalex.org/W1967424056","https://openalex.org/W868043274","https://openalex.org/W2513523087","https://openalex.org/W1187916458","https://openalex.org/W2373861055","https://openalex.org/W2063575861","https://openalex.org/W1967080779","https://openalex.org/W2612632602"],"abstract_inverted_index":{"Today's":[0],"rapidly":[1],"growing":[2],"document":[3,10,43,77],"volumes":[4],"pose":[5],"pressing":[6],"challenges":[7,70],"to":[8,30,40,75,93],"modern":[9],"analytics,":[11],"in":[12,33,71],"both":[13,34],"space":[14,109],"usage":[15],"and":[16,80,86,110,126],"processing":[17,29,98,118],"time.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"propose":[23],"the":[24,51,68,73],"concept":[25,52],"of":[26,84],"compression-based":[27,96],"direct":[28,42,97],"alleviate":[31],"issues":[32],"dimensions.":[35],"The":[36],"main":[37],"idea":[38,74],"is":[39],"enable":[41],"analytics":[44,78],"on":[45,56,123,128,131],"compressed":[46],"data.":[47],"We":[48,66],"present":[49],"how":[50],"can":[53],"be":[54],"materialized":[55],"Sequitur,":[57],"a":[58,82],"compression":[59],"algorithm":[60],"that":[61,102],"produces":[62],"hierarchical":[63],"grammar-like":[64],"representations.":[65],"discuss":[67],"major":[69],"applying":[72],"various":[76],"tasks,":[79],"reveal":[81],"set":[83],"guidelines":[85],"also":[87],"assistant":[88],"software":[89],"modules":[90],"for":[91],"developers":[92],"effectively":[94],"apply":[95],".":[99],"Experiments":[100],"show":[101],"our":[103],"proposed":[104],"techniques":[105],"save":[106],"90.8%":[107],"storage":[108],"77.5%":[111],"memory":[112],"usage,":[113],"while":[114],"speeding":[115],"up":[116],"data":[117],"significantly,":[119],"i.e.,":[120],"by":[121],"1.6X":[122],"sequential":[124],"systems,":[125],"2.2X":[127],"distributed":[129],"clusters,":[130],"average.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}