{"id":"https://openalex.org/W2071218019","doi":"https://doi.org/10.1145/1871437.1871551","title":"Estimating accuracy for text classification tasks on large unlabeled data","display_name":"Estimating accuracy for text classification tasks on large unlabeled data","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2071218019","doi":"https://doi.org/10.1145/1871437.1871551","mag":"2071218019"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041254552","display_name":"Snigdha Chaturvedi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Snigdha Chaturvedi","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004954473","display_name":"Tanveer A. Faruquie","orcid":"https://orcid.org/0009-0008-9474-7928"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanveer A. Faruquie","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110629023","display_name":"L. Venkata Subramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"L. Venkata Subramaniam","raw_affiliation_strings":["IBM Research India, New Delhi, India","IBM Research-India, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM Research-India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukesh K. Mohania","raw_affiliation_strings":["IBM India Software Lab, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Software Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"889","last_page":"898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9958999752998352,"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":0.812119722366333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6524083614349365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6251398324966431},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5961266756057739},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5906009674072266},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4698064923286438},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4450329840183258},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4407981038093567},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4322599768638611},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.42432859539985657},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19388249516487122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812119722366333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6524083614349365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6251398324966431},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5961266756057739},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5906009674072266},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4698064923286438},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4450329840183258},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4407981038093567},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4322599768638611},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.42432859539985657},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19388249516487122},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1479807131","https://openalex.org/W1494580925","https://openalex.org/W1519451279","https://openalex.org/W1604938182","https://openalex.org/W1964357740","https://openalex.org/W1995220928","https://openalex.org/W1996956037","https://openalex.org/W2038181716","https://openalex.org/W2073251771","https://openalex.org/W2113765418","https://openalex.org/W2142334564","https://openalex.org/W2151023586","https://openalex.org/W2156515921","https://openalex.org/W2158188757","https://openalex.org/W2160806787","https://openalex.org/W2326325773","https://openalex.org/W2553530424","https://openalex.org/W3103913776","https://openalex.org/W6628939419","https://openalex.org/W6641163509"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W4287241967","https://openalex.org/W3144173820","https://openalex.org/W3104108945","https://openalex.org/W2033364610","https://openalex.org/W2168489430"],"abstract_inverted_index":{"Rule":[0],"based":[1,21,35,71,195],"systems":[2,36],"for":[3,172],"processing":[4,176],"text":[5,175],"data":[6,27,96,132],"encode":[7],"the":[8,25,29,65,74,88,102,105,130,135,150,163],"knowledge":[9],"of":[10,24,55,59,104,129,134,138,152],"a":[11,15,42,93,113,127,146,153,157],"human":[12,192],"expert":[13],"into":[14],"rule":[16,30,194],"base":[17],"to":[18,45,124,148],"take":[19],"decisions":[20,47],"on":[22,48,64,72,85,92,108,156,169],"interactions":[23],"input":[26],"and":[28,50,119,180,184,191],"base.":[31],"Similarly,":[32],"supervised":[33,187],"learning":[34,75,189],"can":[37],"learn":[38],"patterns":[39],"present":[40,145],"in":[41],"given":[43,154],"dataset":[44,159],"make":[46],"similar":[49],"other":[51],"related":[52],"data.":[53,164],"Performances":[54],"both":[56,186],"these":[57],"classes":[58],"models":[60,81,107],"are":[61],"largely":[62],"dependent":[63],"training":[66,86],"examples":[67],"seen":[68],"by":[69],"them,":[70],"which":[73,120],"was":[76],"performed.":[77],"Even":[78],"though":[79],"trained":[80],"might":[82],"fit":[83],"well":[84],"data,":[87],"accuracies":[89],"they":[90],"yield":[91],"new":[94,109,131,158],"test":[95],"may":[97],"be":[98],"considerably":[99],"different.":[100],"Computing":[101],"accuracy":[103,151],"learnt":[106],"unlabeled":[110],"datasets":[111,139,171],"is":[112,121],"challenging":[114],"problem":[115],"requiring":[116],"costly":[117],"labeling,":[118],"still":[122],"likely":[123],"only":[125],"cover":[126],"subset":[128],"because":[133],"large":[136,170],"sizes":[137],"involved.":[140],"In":[141],"this":[142],"paper,":[143],"we":[144],"method":[147,168],"estimate":[149],"model":[155],"without":[160],"manually":[161],"labeling":[162],"We":[165],"verify":[166],"our":[167],"two":[173],"shallow":[174],"tasks:":[177],"document":[178],"classification":[179],"postal":[181],"address":[182],"segmentation,":[183],"using":[185],"machine":[188],"methods":[190],"generated":[193],"models.":[196]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}