{"id":"https://openalex.org/W2530223335","doi":"https://doi.org/10.1631/fitee.1500332","title":"TextGen: a realistic text data content generation method for modern storage system benchmarks","display_name":"TextGen: a realistic text data content generation method for modern storage system benchmarks","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2530223335","doi":"https://doi.org/10.1631/fitee.1500332","mag":"2530223335"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.1500332","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1500332","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","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/A5078115749","display_name":"Longxiang Wang","orcid":"https://orcid.org/0000-0003-2005-114X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long-xiang Wang","raw_affiliation_strings":["School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332436","display_name":"Xiaoshe Dong","orcid":"https://orcid.org/0000-0002-9003-2625"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-she Dong","raw_affiliation_strings":["School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062123451","display_name":"Xingjun Zhang","orcid":"https://orcid.org/0000-0003-1434-7016"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing-jun Zhang","raw_affiliation_strings":["School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055235315","display_name":"Yinfeng Wang","orcid":"https://orcid.org/0000-0002-4597-7136"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin-feng Wang","raw_affiliation_strings":["Shenzhen Institute of Information Technology, Shenzhen, 518172, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Information Technology, Shenzhen, 518172, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080898240","display_name":"Tao Ju","orcid":"https://orcid.org/0000-0002-5850-4565"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ju","raw_affiliation_strings":["School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082976078","display_name":"Guofu Feng","orcid":"https://orcid.org/0000-0002-6390-2066"},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-fu Feng","raw_affiliation_strings":["College of Information Technology, Shanghai Ocean University, Shanghai, 201306, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Technology, Shanghai Ocean University, Shanghai, 201306, China","institution_ids":["https://openalex.org/I44675526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4772,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8520701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","issue":"10","first_page":"982","last_page":"993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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/T11478","display_name":"Caching and Content Delivery","score":0.9779000282287598,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8292974233627319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773008406162262},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7000321745872498},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5776026248931885},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.5423002243041992},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42370089888572693}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8292974233627319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773008406162262},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7000321745872498},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5776026248931885},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5423002243041992},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42370089888572693},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.1500332","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1500332","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1509371880","https://openalex.org/W1514528578","https://openalex.org/W1522061241","https://openalex.org/W1559956479","https://openalex.org/W1822146434","https://openalex.org/W1934045625","https://openalex.org/W1964802076","https://openalex.org/W1965612527","https://openalex.org/W1968625547","https://openalex.org/W1976118356","https://openalex.org/W1985229168","https://openalex.org/W2029190513","https://openalex.org/W2054137409","https://openalex.org/W2057985970","https://openalex.org/W2069906566","https://openalex.org/W2070641109","https://openalex.org/W2090330503","https://openalex.org/W2097382465","https://openalex.org/W2102248717","https://openalex.org/W2107745473","https://openalex.org/W2119878143","https://openalex.org/W2119885577","https://openalex.org/W2121884932","https://openalex.org/W2138523425","https://openalex.org/W2142905080","https://openalex.org/W2143730413","https://openalex.org/W2155729921","https://openalex.org/W2159081928","https://openalex.org/W2160127232","https://openalex.org/W2170521549","https://openalex.org/W2172096705","https://openalex.org/W2240667924","https://openalex.org/W4235017537","https://openalex.org/W6601092777","https://openalex.org/W6602694123","https://openalex.org/W6642459659","https://openalex.org/W7075727625"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Modern":[0],"storage":[1,24,40,84,107,156],"systems":[2,108],"incorporate":[3],"data":[4,15,44,57,71,79,150,183,220],"compressors":[5],"to":[6,34,49,55,69,191,205,240],"improve":[7,182],"their":[8],"performance":[9,86,125,254],"and":[10,42,131,169,255],"capacity.":[11],"As":[12],"a":[13,23,38,52,91,147,171,192,273],"result,":[14],"content":[16,72,151],"can":[17],"significantly":[18],"influence":[19,82,123],"the":[20,62,75,83,88,101,120,128,137,161,179,186,218,225,252,259],"result":[21,63,103],"of":[22,77,90,212,228,258,275],"system":[25,85,157],"benchmark.":[26,92],"Because":[27],"real-world":[28,78,166,236,267],"proprietary":[29],"datasets":[30,237,260,268],"are":[31,134],"too":[32],"large":[33],"be":[35,46],"copied":[36],"onto":[37],"test":[39],"system,":[41],"most":[43],"cannot":[45,98],"shared":[47],"due":[48],"privacy":[50],"issues,":[51],"benchmark":[53,102],"needs":[54],"generate":[56,70,206],"synthetically.":[58],"To":[59,140,181,232],"ensure":[60],"that":[61,81,100,109,117,122,224],"is":[64,67,104,116,189,203,230,278],"accurate,":[65],"it":[66],"necessary":[68],"based":[73],"on":[74,217],"characterization":[76],"properties":[80,121,133],"during":[87],"execution":[89],"The":[93,114,199,209,244],"existing":[94],"approach,":[95],"called":[96],"SDGen,":[97,251],"guarantee":[99],"accurate":[105],"in":[106,178],"have":[110],"built-in":[111],"word-based":[112,276],"compressors.":[113],"reason":[115],"SDGen":[118],"characterizes":[119],"compression":[124,253,256],"only":[126,216],"at":[127,136],"byte":[129],"level,":[130],"no":[132],"characterized":[135],"word":[138,162,177],"level.":[139],"address":[141],"this":[142],"problem,":[143],"we":[144],"present":[145],"TextGen,":[146,234],"realistic":[148],"text":[149,167],"generation":[152,184,214],"method":[153],"for":[154],"modern":[155],"benchmarks.":[158],"TextGen":[159,213,229,263],"builds":[160],"corpus":[163],"by":[164,174,195,262],"segmenting":[165],"datasets,":[168],"creates":[170],"word-frequency":[172,187],"distribution":[173,188,194],"counting":[175],"each":[176],"corpus.":[180],"performance,":[185],"fitted":[190],"lognormal":[193],"maximum":[196],"likelihood":[197],"estimation.":[198],"Monte":[200],"Carlo":[201],"approach":[202],"used":[204,239],"synthetic":[207],"data.":[208],"running":[210],"time":[211,226],"depends":[215],"expected":[219],"size,":[221],"which":[222],"means":[223],"complexity":[227],"O(n).":[231],"evaluate":[233],"four":[235],"were":[238],"perform":[241],"an":[242],"experiment.":[243],"experimental":[245],"results":[246],"show":[247],"that,":[248],"compared":[249],"with":[250],"ratio":[257],"generated":[261],"deviate":[264],"less":[265],"from":[266],"when":[269],"end-tagged":[270],"dense":[271],"code,":[272],"representative":[274],"compressors,":[277],"evaluated.":[279]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}