{"id":"https://openalex.org/W2043116698","doi":"https://doi.org/10.1145/1996130.1996174","title":"A distributed look-up architecture for text mining applications using mapreduce","display_name":"A distributed look-up architecture for text mining applications using mapreduce","publication_year":2011,"publication_date":"2011-06-08","ids":{"openalex":"https://openalex.org/W2043116698","doi":"https://doi.org/10.1145/1996130.1996174","mag":"2043116698","pmid":"https://pubmed.ncbi.nlm.nih.gov/25356441"},"language":"en","primary_location":{"id":"doi:10.1145/1996130.1996174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"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/A5086058099","display_name":"Atilla Soner Balkir","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atilla Soner Balkir","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA","University of Chicago , Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Chicago , Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA","University of Chicago , Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Chicago , Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004739989","display_name":"Andrey Rzhetsky","orcid":"https://orcid.org/0000-0001-6959-7405"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrey Rzhetsky","raw_affiliation_strings":["Computation Institute, Chicago, IL, USA","Departments of Medicine and Human Genetics, Computation Institute, Institute for Genomics and Systems Biology, University of Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computation Institute, Chicago, IL, USA","institution_ids":[]},{"raw_affiliation_string":"Departments of Medicine and Human Genetics, Computation Institute, Institute for Genomics and Systems Biology, University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2011","issue":null,"first_page":"279","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9983999729156494,"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":0.9983999729156494,"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/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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.8983415365219116},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5872886180877686},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5417822003364563},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5248700976371765},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.5175656676292419},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.49665576219558716},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4288523197174072},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4272671937942505},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41902631521224976},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3849825859069824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17548149824142456},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10270479321479797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8983415365219116},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5872886180877686},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5417822003364563},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5248700976371765},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.5175656676292419},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.49665576219558716},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4288523197174072},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4272671937942505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41902631521224976},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3849825859069824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17548149824142456},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10270479321479797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1996130.1996174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed computing","raw_type":"proceedings-article"},{"id":"pmid:25356441","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25356441","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... International Symposium on High Performance Distributed Computing","raw_type":null},{"id":"pmh:oai:europepmc.org:3176514","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4209700","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3825053653","display_name":null,"funder_award_id":"R01 LM010132","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G7018261021","display_name":null,"funder_award_id":"R01 GM061372","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W48481975","https://openalex.org/W145937141","https://openalex.org/W1976860187","https://openalex.org/W2006969979","https://openalex.org/W2102130607","https://openalex.org/W2109664771","https://openalex.org/W2109722477","https://openalex.org/W2122228338","https://openalex.org/W2122410182","https://openalex.org/W2123845384","https://openalex.org/W2127797489","https://openalex.org/W2132399973","https://openalex.org/W2136579661","https://openalex.org/W2140551944","https://openalex.org/W2145766604","https://openalex.org/W2148212498","https://openalex.org/W2167927436","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2412336808","https://openalex.org/W2624304035","https://openalex.org/W2950627632"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W2086572746","https://openalex.org/W3171007296","https://openalex.org/W2604468458","https://openalex.org/W2157216338","https://openalex.org/W22115721","https://openalex.org/W1662107788","https://openalex.org/W121740227","https://openalex.org/W3082379938","https://openalex.org/W2135966669"],"abstract_inverted_index":{"Text":[0],"mining":[1],"applications":[2],"typically":[3],"involve":[4],"statistical":[5],"models":[6,26],"that":[7,47,76],"require":[8],"accessing":[9],"and":[10,31,69,108],"updating":[11],"model":[12,49],"parameters":[13,50],"in":[14,65,97],"an":[15,109],"iterative":[16],"fashion.":[17],"With":[18],"the":[19,23,38,87,92],"growing":[20],"size":[21],"of":[22,41,91,116],"data,":[24],"such":[25],"become":[27],"extremely":[28],"parameter":[29],"rich,":[30],"naive":[32],"parallel":[33],"implementations":[34],"fail":[35],"to":[36,51,59],"address":[37],"scalability":[39],"problem":[40,82],"maintaining":[42],"a":[43,71,102],"distributed":[44],"look-up":[45,74],"table":[46],"maps":[48],"their":[52],"values.":[53],"We":[54],"evaluate":[55],"several":[56],"existing":[57],"alternatives":[58],"provide":[60],"coordination":[61],"among":[62],"worker":[63],"nodes":[64],"Hadoop":[66],"[11]":[67],"clusters,":[68],"suggest":[70],"new":[72],"multi-layered":[73],"architecture":[75],"is":[77],"specifically":[78],"optimized":[79],"for":[80],"certain":[81],"domains.":[83],"Our":[84],"solution":[85],"exploits":[86],"power-law":[88],"distribution":[89],"characteristics":[90],"phrase":[93],"or":[94],"n-gram":[95],"counts":[96],"large":[98],"corpora":[99],"while":[100],"utilizing":[101],"Bloom":[103],"Filter":[104],"[2],":[105],"in-memory":[106],"cache,":[107],"HBase":[110],"[12]":[111],"cluster":[112],"at":[113],"varying":[114],"levels":[115],"abstraction.":[117]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
