{"id":"https://openalex.org/W2112667785","doi":"https://doi.org/10.1145/2486767.2486774","title":"GPText","display_name":"GPText","publication_year":2013,"publication_date":"2013-06-23","ids":{"openalex":"https://openalex.org/W2112667785","doi":"https://doi.org/10.1145/2486767.2486774","mag":"2112667785"},"language":"en","primary_location":{"id":"doi:10.1145/2486767.2486774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2486767.2486774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Data Analytics in the Cloud","raw_type":"proceedings-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/A5100377517","display_name":"Kun Li","orcid":"https://orcid.org/0000-0001-8501-3916"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kun Li","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070860161","display_name":"Christan Grant","orcid":"https://orcid.org/0000-0002-6684-3620"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christan Grant","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003464266","display_name":"Daisy Zhe Wang","orcid":"https://orcid.org/0009-0003-8234-5482"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daisy Zhe Wang","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035145169","display_name":"Sunny Khatri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunny Khatri","raw_affiliation_strings":["Greenplum, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Greenplum, San Mateo, CA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029596944","display_name":"George Chitouras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Chitouras","raw_affiliation_strings":["Greenplum, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Greenplum, San Mateo, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100377517"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":4.8537,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95219481,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"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":0.9973999857902527,"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/T11106","display_name":"Data Management and Algorithms","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8675459623336792},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7609347701072693},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6899172067642212},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.601662814617157},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.567261815071106},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4948388934135437},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4948353171348572},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.4814697802066803},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.47759032249450684},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.4436679780483246},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36925244331359863},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2801574468612671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27758827805519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675459623336792},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7609347701072693},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6899172067642212},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.601662814617157},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.567261815071106},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4948388934135437},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4948353171348572},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.4814697802066803},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.47759032249450684},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.4436679780483246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36925244331359863},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2801574468612671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27758827805519104},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2486767.2486774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2486767.2486774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Data Analytics in the Cloud","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3372681642","display_name":null,"funder_award_id":"DGE-0802270","funder_id":"https://openalex.org/F4320337368","funder_display_name":"Division of Graduate Education"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1515847863","https://openalex.org/W1674586686","https://openalex.org/W1972015017","https://openalex.org/W2044849727","https://openalex.org/W2090850279","https://openalex.org/W2135779000","https://openalex.org/W2146635036","https://openalex.org/W2162829716","https://openalex.org/W2185715143","https://openalex.org/W6686688631","https://openalex.org/W7062434573"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2111726165","https://openalex.org/W2347460059","https://openalex.org/W2383168085","https://openalex.org/W2264386184","https://openalex.org/W1729122178"],"abstract_inverted_index":{"Many":[0],"companies":[1],"keep":[2],"large":[3],"amounts":[4],"of":[5,9,158],"text":[6,47,67],"data":[7,28,38],"inside":[8],"relational":[10],"databases.":[11],"Several":[12],"challenges":[13],"exist":[14],"in":[15,83],"using":[16,106],"state-of-the-art":[17],"systems":[18],"to":[19,36,54,137,139],"perform":[20],"analysis":[21,68],"on":[22,120,170],"such":[23,101,144],"datasets.":[24,57],"First,":[25],"expensive":[26],"big":[27],"transfer":[29],"cost":[30],"must":[31],"be":[32,118],"paid":[33],"up":[34,53],"front":[35],"move":[37],"between":[39],"databases":[40],"and":[41,79,97,104,122,129,148,156],"analytics":[42,48,115],"systems.":[43],"Second,":[44],"many":[45],"popular":[46],"packages":[49],"do":[50],"not":[51],"scale":[52],"production":[55],"sized":[56],"In":[58,124],"this":[59],"paper,":[60],"we":[61,164],"introduce":[62],"GPText,":[63],"Greenplum":[64],"parallel":[65,86,160],"statistical":[66,77,99],"framework":[69],"that":[70],"addresses":[71],"the":[72,93,154,159,171],"above":[73],"problems":[74],"by":[75],"supporting":[76],"inference":[78],"learning":[80],"algorithms":[81,100],"natively":[82],"a":[84,131],"massively":[85],"processing":[87],"database":[88],"system.":[89],"GPText":[90,126,172],"seamlessly":[91],"integrates":[92],"Solr":[94],"search":[95],"engine":[96],"applies":[98],"as":[102,145],"k-means":[103],"LDA":[105],"MADLib,":[107],"an":[108,166],"open":[109],"source":[110],"library":[111],"for":[112],"scalable":[113],"in-database":[114],"which":[116],"can":[117],"installed":[119],"Post-greSQL":[121],"Greenplum.":[123],"addition,":[125],"also":[127],"developed":[128],"contributed":[130],"linear-chain":[132],"conditional":[133],"random":[134],"field(CRF)":[135],"module":[136],"MADLib":[138],"enable":[140],"information":[141],"extraction":[142],"tasks":[143],"part-of-speech":[146],"tagging":[147],"named":[149],"entity":[150],"recognition.":[151],"We":[152],"show":[153],"performance":[155],"scalability":[157],"CRF":[161],"implementation.":[162],"Finally,":[163],"describe":[165],"eDiscovery":[167],"application":[168],"built":[169],"framework.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
