{"id":"https://openalex.org/W1985228917","doi":"https://doi.org/10.1109/bigdata.2014.7004355","title":"Feature selection for text clustering in limited memory using Monte Carlo wrapper","display_name":"Feature selection for text clustering in limited memory using Monte Carlo wrapper","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1985228917","doi":"https://doi.org/10.1109/bigdata.2014.7004355","mag":"1985228917"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5077747661","display_name":"Vinay Deolalikar","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vinay Deolalikar","raw_affiliation_strings":["Hewlett-Packard Research","Hewlett Packard Research"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Research","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Research","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077747661"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0600825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"400","issue":null,"first_page":"42","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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/T10637","display_name":"Advanced Clustering Algorithms Research","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/T11269","display_name":"Algorithms and Data Compression","score":0.9970999956130981,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8878103494644165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7696336507797241},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6071949005126953},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.580374538898468},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5770699381828308},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5620915293693542},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5585572123527527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5423735976219177},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5140998959541321},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4645390808582306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4573816955089569},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.44553473591804504},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.442894846200943},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.4381634294986725},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.43422067165374756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3608850836753845}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8878103494644165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696336507797241},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6071949005126953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.580374538898468},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5770699381828308},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5620915293693542},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5585572123527527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5423735976219177},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5140998959541321},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4645390808582306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4573816955089569},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.44553473591804504},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.442894846200943},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4381634294986725},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.43422067165374756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3608850836753845},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1526719228","https://openalex.org/W1605211498","https://openalex.org/W1619226191","https://openalex.org/W1651093245","https://openalex.org/W1849729440","https://openalex.org/W1890873505","https://openalex.org/W1921984393","https://openalex.org/W1971318281","https://openalex.org/W2001907516","https://openalex.org/W2005422315","https://openalex.org/W2040884411","https://openalex.org/W2050516752","https://openalex.org/W2067462817","https://openalex.org/W2099322651","https://openalex.org/W2102831150","https://openalex.org/W2103333826","https://openalex.org/W2109535575","https://openalex.org/W2116237179","https://openalex.org/W2116459725","https://openalex.org/W2133462743","https://openalex.org/W2435251607","https://openalex.org/W4235023610","https://openalex.org/W4292023222","https://openalex.org/W6637231022","https://openalex.org/W6638875480","https://openalex.org/W6639419968","https://openalex.org/W6662778435","https://openalex.org/W6674952872","https://openalex.org/W6675969814","https://openalex.org/W6677504887","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2622412490","https://openalex.org/W2087424554","https://openalex.org/W2385630304","https://openalex.org/W1957537378","https://openalex.org/W2393707058","https://openalex.org/W2101637161","https://openalex.org/W2590117803","https://openalex.org/W2152187121","https://openalex.org/W2187529160"],"abstract_inverted_index":{"Feature":[0],"selection":[1,14,29,47,131],"is":[2,33],"a":[3,139],"natural":[4],"choice":[5],"of":[6,38,57,80,112,118],"technique":[7],"to":[8,23,35,72,96,126,137,142],"scale":[9],"up":[10],"clustering.":[11,42],"However,":[12],"feature":[13,28,46,130],"for":[15,30,45,48],"clustering":[16,50,56,120,140,156],"has":[17],"received":[18],"scant":[19],"research":[20],"attention":[21],"compared":[22],"the":[24,36,58,81,100,105,108,113,116,119,123],"vast":[25],"literature":[26,53],"on":[27,146],"classification.":[31],"This":[32],"due":[34],"absence":[37],"class":[39],"labels":[40],"in":[41,52,157],"The":[43],"approaches":[44],"text":[49,148],"proposed":[51],"require":[54,90],"(repeated)":[55],"entire":[59,82,101],"corpus.":[60],"We":[61,87,103],"demonstrate":[62],"that":[63],"we":[64,134],"can,":[65],"instead,":[66],"apply":[67],"Monte":[68],"Carlo":[69],"(MC)":[70],"techniques":[71],"\u201ccollect\u201d":[73],"features":[74,95],"by":[75],"inspecting":[76],"only":[77],"tiny":[78],"portions":[79],"dataset":[83],"at":[84],"any":[85,91],"time.":[86],"do":[88],"not":[89],"global":[92],"information":[93],"about":[94],"be":[97],"computed":[98],"over":[99],"dataset.":[102],"evaluate":[104],"trade-offs":[106],"between":[107],"various":[109],"cost":[110],"parameters":[111],"MC":[114],"with":[115],"efficacy":[117],"produced":[121],"and":[122],"time":[124,155],"taken":[125],"produce":[127],"it.":[128],"Doing":[129],"using":[132,160],"MC,":[133],"are":[135],"able":[136],"perform":[138],"three":[141],"four":[143],"times":[144],"faster":[145],"standard":[147],"benchmarks.":[149],"Such":[150],"speed-up":[151],"can":[152],"enable":[153],"near-real":[154],"enterprise":[158],"workflows":[159],"limited":[161],"memory.":[162]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}