{"id":"https://openalex.org/W2932581631","doi":null,"title":"GOGGLES: Automatic Training Data Generation with Affinity Coding.","display_name":"GOGGLES: Automatic Training Data Generation with Affinity Coding.","publication_year":2019,"publication_date":"2019-03-11","ids":{"openalex":"https://openalex.org/W2932581631","mag":"2932581631"},"language":"en","primary_location":{"id":"mag:2932581631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.04552.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.04552.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036502813","display_name":"Nilaksh Das","orcid":"https://orcid.org/0000-0002-5281-5549","observed_orcids":["https://orcid.org/0000-0002-5281-5549"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nilaksh Das","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5281-5549","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020206458","display_name":"Sanya Chaba","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanya Chaba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103908223","display_name":"Sakshi Gandhi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakshi Gandhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020153026","display_name":"Duen Horng Chau","orcid":"https://orcid.org/0000-0001-9824-3323","observed_orcids":["https://orcid.org/0000-0001-9824-3323"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duen Horng Chau","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9824-3323","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100430982","display_name":"Xu Chu","orcid":"https://orcid.org/0009-0007-3202-3767","observed_orcids":["https://orcid.org/0009-0007-3202-3767"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Chu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0007-3202-3767","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9223999977111816,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9223999977111816,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.053700000047683716,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.010599999688565731,"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/automatic-training-data-generation","display_name":"automatic training data generation","score":0.8989999890327454},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.9150000214576721},{"id":"https://openalex.org/keywords/data-programming","display_name":"data programming","score":0.7739999890327454},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.6309999823570251},{"id":"https://openalex.org/keywords/semantic-prototypes","display_name":"semantic prototypes","score":0.8939999938011169},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8349999785423279},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.8960000276565552},{"id":"https://openalex.org/keywords/label-inference","display_name":"label inference","score":0.7329999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367360591888428},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.568446934223175},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.528717577457428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5262707471847534},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5061885714530945},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5029630064964294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4629092812538147},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4207681119441986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40701526403427124},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40677016973495483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0911095142364502},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","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":1,"locations":[{"id":"mag:2932581631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.04552.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2932581631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.04552.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1487602158","https://openalex.org/W1494076862","https://openalex.org/W1663973292","https://openalex.org/W1686810756","https://openalex.org/W1797268635","https://openalex.org/W1849277567","https://openalex.org/W2008824967","https://openalex.org/W2010382953","https://openalex.org/W2049633694","https://openalex.org/W2067713319","https://openalex.org/W2089468765","https://openalex.org/W2107254606","https://openalex.org/W2136504847","https://openalex.org/W2153138487","https://openalex.org/W2161381512","https://openalex.org/W2161969291","https://openalex.org/W2165698076","https://openalex.org/W2404161646","https://openalex.org/W2404544029","https://openalex.org/W2441563267","https://openalex.org/W2591700809","https://openalex.org/W2769041395","https://openalex.org/W2775018596","https://openalex.org/W2788633781","https://openalex.org/W2800292742","https://openalex.org/W2911424454","https://openalex.org/W2911906319","https://openalex.org/W2937153231","https://openalex.org/W2950180292","https://openalex.org/W2950873798","https://openalex.org/W2953391683","https://openalex.org/W2962843773","https://openalex.org/W2963499153","https://openalex.org/W3034942609"],"related_works":["https://openalex.org/W3030888939","https://openalex.org/W2404161646","https://openalex.org/W4406279584","https://openalex.org/W4235216760","https://openalex.org/W3021557699","https://openalex.org/W3034712684","https://openalex.org/W7054010995","https://openalex.org/W3173968209","https://openalex.org/W2990891113","https://openalex.org/W3167788848"],"abstract_inverted_index":{"Generating":[0],"large":[1],"labeled":[2],"training":[3,35,108],"data":[4,19,26,36,62,71,165,230],"is":[5,52,179,255],"becoming":[6],"the":[7,25,31,68,76,86,113,116,125,147,161,222,228,242,248],"biggest":[8],"bottleneck":[9],"in":[10,24,34,239],"building":[11],"and":[12,83,119],"deploying":[13],"supervised":[14],"machine":[15],"learning":[16],"models.":[17],"Recently,":[18],"programming":[20,39,72,231],"has":[21],"been":[22],"proposed":[23],"management":[27],"community":[28],"to":[29,42,93,227],"reduce":[30],"human":[32,169],"cost":[33],"generation.":[37],"Data":[38],"expects":[40],"users":[41,90],"write":[43],"a":[44,53,59,100,174],"set":[45],"of":[46,50,61,70,80,85,107,134,157,163,182,241,244],"labeling":[47,87,186,250],"functions,":[48],"each":[49],"which":[51],"weak":[54,135,158],"supervision":[55,159],"source":[56],"that":[57,89,121,178],"labels":[58,245],"subset":[60],"points":[63],"with":[64],"better-than-random":[65],"accuracy.":[66],"However,":[67],"success":[69],"heavily":[73],"depends":[74],"on":[75,201,221],"quality":[77,243],"(in":[78],"terms":[79,240],"both":[81],"accuracy":[82],"coverage)":[84],"functions":[88],"still":[91],"need":[92],"design":[94],"manually.":[95],"\r\nWe":[96],"propose":[97,173],"affinity":[98,111,148,183,195,224],"coding,":[99,112],"new":[101],"paradigm":[102],"for":[103,137,185,193,215,247],"fully":[104],"automatic":[105],"generation":[106],"data.":[109],"In":[110],"similarity":[114,145],"between":[115],"unlabeled":[117,127,164],"instances":[118,128],"prototypes":[203],"are":[122],"derived":[123],"from":[124,197,205],"same":[126],"serve":[129],"as":[130,146,154,160,209,211],"signals":[131],"(or":[132],"sources":[133,156],"supervision)":[136],"determining":[138],"class":[139,217],"membership.":[140],"We":[141,171],"term":[142],"this":[143,258],"implicit":[144],"score.":[149],"Consequently,":[150],"we":[151],"can":[152],"have":[153],"many":[155],"number":[162],"points,":[166],"without":[167],"any":[168],"input.":[170],"also":[172],"system":[175,232,254],"called":[176],"GOGGLES":[177,189,234,253],"an":[180,212],"implementation":[181],"coding":[184],"image":[187,198],"datasets.":[188],"features":[190],"novel":[191],"techniques":[192],"deriving":[194],"scores":[196],"datasets":[199],"based":[200,220],"semantic":[202],"extracted":[204],"convolutional":[206],"neural":[207],"nets,":[208],"well":[210],"expectation-maximization":[213],"approach":[214],"performing":[216],"label":[218],"inference":[219],"computed":[223],"scores.":[225],"\r\nCompared":[226],"state-of-the-art":[229],"Snorkel,":[233],"exhibits":[235],"14.88%":[236],"average":[237],"improvement":[238],"generated":[246],"binary":[249],"task.":[251],"The":[252],"open-sourced":[256],"at":[257],"https":[259],"URL.":[260]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-04-11T00:00:00"}