{"id":"https://openalex.org/W2514021172","doi":"https://doi.org/10.5220/0005943000250030","title":"Comparison of Distributed Computing Approaches to Complexity of n-gram Extraction","display_name":"Comparison of Distributed Computing Approaches to Complexity of n-gram Extraction","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2514021172","doi":"https://doi.org/10.5220/0005943000250030","mag":"2514021172"},"language":"en","primary_location":{"id":"doi:10.5220/0005943000250030","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005943000250030","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Data Management Technologies and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005943000250030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006097846","display_name":"Sanzhar Aubakirov","orcid":"https://orcid.org/0000-0002-8416-527X"},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Sanzhar Aubakirov","raw_affiliation_strings":["al-Farabi Kazakh National University, Kazakhstan","Department of Computer Science, al-Farabi Kazakh National University, Almaty, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"al-Farabi Kazakh National University, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]},{"raw_affiliation_string":"Department of Computer Science, al-Farabi Kazakh National University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006360142","display_name":"Paulo Trigo","orcid":"https://orcid.org/0000-0001-5850-615X"},"institutions":[{"id":"https://openalex.org/I203847022","display_name":"Instituto Polit\u00e9cnico de Lisboa","ror":"https://ror.org/04ea70f07","country_code":"PT","type":"education","lineage":["https://openalex.org/I203847022"]},{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paulo Trigo","raw_affiliation_strings":["Instituto Superior de Engenharia de Lisboa and Biosystems and Integrative Sciences Institute / Agent and Systems Modeling, Portugal","Instituto Superior de Engenharia de Lisboa, Biosystems and Integrative Sciences Institute / Agent and Systems Modeling, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto Superior de Engenharia de Lisboa and Biosystems and Integrative Sciences Institute / Agent and Systems Modeling, Portugal","institution_ids":["https://openalex.org/I4210125590"]},{"raw_affiliation_string":"Instituto Superior de Engenharia de Lisboa, Biosystems and Integrative Sciences Institute / Agent and Systems Modeling, Lisbon, Portugal","institution_ids":["https://openalex.org/I203847022"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113847579","display_name":"Darhan Ahmed-Zaki","orcid":null},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Darhan Ahmed-Zaki","raw_affiliation_strings":["al-Farabi Kazakh National University, Kazakhstan","Department of Computer Science, al-Farabi Kazakh National University, Almaty, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"al-Farabi Kazakh National University, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]},{"raw_affiliation_string":"Department of Computer Science, al-Farabi Kazakh National University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006097846"],"corresponding_institution_ids":["https://openalex.org/I185571130"],"apc_list":null,"apc_paid":null,"fwci":0.6929,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80064155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9937000274658203,"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":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8611016273498535},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8143395185470581},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.7641063928604126},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6582922339439392},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6213403344154358},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5666530132293701},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5138583183288574},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5135226845741272},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.46084901690483093},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.42455318570137024},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4189216196537018},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3740569055080414},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37098264694213867},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3106982707977295},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19086462259292603},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16044297814369202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1587270200252533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611016273498535},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8143395185470581},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7641063928604126},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6582922339439392},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6213403344154358},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5666530132293701},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5138583183288574},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5135226845741272},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.46084901690483093},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.42455318570137024},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4189216196537018},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3740569055080414},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37098264694213867},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3106982707977295},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19086462259292603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16044297814369202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1587270200252533},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0005943000250030","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005943000250030","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Data Management Technologies and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.ipl.pt:10400.21/6854","is_oa":true,"landing_page_url":"http://hdl.handle.net/10400.21/6854","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference object"}],"best_oa_location":{"id":"doi:10.5220/0005943000250030","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005943000250030","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Data Management Technologies and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"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":7,"referenced_works":["https://openalex.org/W1968756140","https://openalex.org/W1976821017","https://openalex.org/W2109664771","https://openalex.org/W2111103371","https://openalex.org/W2131166445","https://openalex.org/W2170036644","https://openalex.org/W2397462379"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W4256502920","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2291469010"],"abstract_inverted_index":{"In":[0,40],"this":[1,74],"paper":[2],"we":[3,47,148],"compare":[4],"different":[5,128],"technologies":[6],"that":[7,64,158],"support":[8],"distributed":[9],"computing":[10],"as":[11],"a":[12,28,32,101,109,125,145],"means":[13],"to":[14,38,42,49,151],"address":[15,19],"complex":[16],"tasks.":[17],"We":[18,72,131],"the":[20,69,121,156,175],"task":[21,75],"of":[22,35,96,104,112,127,165,174],"n-gram":[23],"text":[24],"extraction":[25],"which":[26],"is":[27,159],"big":[29],"computational":[30],"given":[31],"large":[33,102,113],"amount":[34],"textual":[36],"data":[37,166],"process.":[39],"order":[41],"deal":[43],"with":[44],"such":[45],"complexity":[46],"have":[48],"adopt":[50],"and":[51,61,85,107,120,134,141,172],"implement":[52],"parallelization":[53,70],"patterns.":[54],"Nowadays":[55],"there":[56],"are":[57,149],"several":[58],"patterns,":[59],"platforms":[60],"even":[62],"languages":[63],"can":[65],"be":[66],"used":[67],"for":[68,124,154,162],"task.":[71],"implemented":[73,92],"on":[76],"three":[77],"platforms:":[78],"(1)":[79],"MPJ":[80,137],"Express,":[81,138],"(2)":[82],"Apache":[83,87,139,142],"Hadoop,":[84],"(3)":[86],"Spark.":[88,143],"The":[89],"experiments":[90],"were":[91],"using":[93],"two":[94],"kinds":[95],"datasets":[97,119],"composed":[98],"by:":[99],"(A)":[100],"number":[103,111],"small":[105,110],"files,":[106],"(B)":[108],"files.":[114],"Each":[115],"experiment":[116,122],"uses":[117],"both":[118],"repeats":[123],"set":[126,167],"file":[129],"sizes.":[130],"compared":[132],"performance":[133],"efficiency":[135],"among":[136],"Hadoop":[140],"As":[144],"final":[146],"result":[147],"able":[150],"provide":[152],"guidelines":[153],"choosing":[155],"platform":[157],"best":[160],"suited":[161],"each":[163],"kind":[164],"regarding":[168],"its":[169],"overall":[170],"size":[171],"granularity":[173],"input":[176],"data.":[177]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
