{"id":"https://openalex.org/W2769041395","doi":"https://doi.org/10.14778/3157794.3157797","title":"Snorkel","display_name":"Snorkel","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2769041395","doi":"https://doi.org/10.14778/3157794.3157797","mag":"2769041395","pmid":"https://pubmed.ncbi.nlm.nih.gov/29770249"},"language":"en","primary_location":{"id":"doi:10.14778/3157794.3157797","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3157794.3157797","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.10160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076215229","display_name":"Alexander Ratner","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexander Ratner","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011117177","display_name":"Stephen H. Bach","orcid":"https://orcid.org/0000-0003-3857-3560"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen H. Bach","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079833242","display_name":"Henry R. Ehrenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Ehrenberg","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028277225","display_name":"Jason Fries","orcid":"https://orcid.org/0000-0001-9316-5768"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Fries","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975637","display_name":"Sen Wu","orcid":"https://orcid.org/0000-0002-6133-4122"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Wu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103852640","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076215229"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":59.0355,"has_fulltext":false,"cited_by_count":741,"citation_normalized_percentile":{"value":0.99882639,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"11","issue":"3","first_page":"269","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9961000084877014,"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":0.9961000084877014,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9958000183105469,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8207216262817383},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7728946208953857},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7666599750518799},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7587442398071289},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5623928904533386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5268893241882324},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.49792981147766113},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4443092942237854},{"id":"https://openalex.org/keywords/subject-matter-expert","display_name":"Subject-matter expert","score":0.4416525661945343},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4178258180618286},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22163188457489014},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13369220495224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207216262817383},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7728946208953857},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7666599750518799},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7587442398071289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5623928904533386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5268893241882324},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.49792981147766113},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4443092942237854},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.4416525661945343},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4178258180618286},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22163188457489014},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13369220495224},{"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/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.14778/3157794.3157797","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3157794.3157797","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmid:29770249","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29770249","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 VLDB Endowment. International Conference on Very Large Data Bases","raw_type":null},{"id":"pmh:oai:arXiv.org:1711.10160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.10160","pdf_url":"https://arxiv.org/pdf/1711.10160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},{"id":"pmh:oai:europepmc.org:4869399","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5951191","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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5951191","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5951191","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings VLDB Endowment","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.10160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.10160","pdf_url":"https://arxiv.org/pdf/1711.10160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W108763474","https://openalex.org/W155855048","https://openalex.org/W398859631","https://openalex.org/W1522301498","https://openalex.org/W1535161492","https://openalex.org/W1541280084","https://openalex.org/W1552847225","https://openalex.org/W1604644367","https://openalex.org/W1731081199","https://openalex.org/W1872614887","https://openalex.org/W1988529147","https://openalex.org/W1991137221","https://openalex.org/W2048679005","https://openalex.org/W2061863227","https://openalex.org/W2068737686","https://openalex.org/W2079735306","https://openalex.org/W2091144449","https://openalex.org/W2097749765","https://openalex.org/W2101654853","https://openalex.org/W2107254606","https://openalex.org/W2107598941","https://openalex.org/W2107907380","https://openalex.org/W2108598243","https://openalex.org/W2111316763","https://openalex.org/W2116064496","https://openalex.org/W2117173982","https://openalex.org/W2122052811","https://openalex.org/W2124001239","https://openalex.org/W2128601422","https://openalex.org/W2132679783","https://openalex.org/W2149713870","https://openalex.org/W2150588363","https://openalex.org/W2152798551","https://openalex.org/W2153138487","https://openalex.org/W2165698076","https://openalex.org/W2169336678","https://openalex.org/W2169585110","https://openalex.org/W2170989440","https://openalex.org/W2194775991","https://openalex.org/W2251405440","https://openalex.org/W2252115292","https://openalex.org/W2335791510","https://openalex.org/W2404161646","https://openalex.org/W2404544029","https://openalex.org/W2466758040","https://openalex.org/W2511082080","https://openalex.org/W2521461771","https://openalex.org/W2578313953","https://openalex.org/W2590501763","https://openalex.org/W2591700809","https://openalex.org/W2592362528","https://openalex.org/W2592549418","https://openalex.org/W2602024037","https://openalex.org/W2604259521","https://openalex.org/W2608353553","https://openalex.org/W2734663976","https://openalex.org/W2753688405","https://openalex.org/W2804236178","https://openalex.org/W2895604144","https://openalex.org/W2903158431","https://openalex.org/W2911424454","https://openalex.org/W2914331073","https://openalex.org/W2915806464","https://openalex.org/W2916047525","https://openalex.org/W2949244208","https://openalex.org/W2949650786","https://openalex.org/W2952865802","https://openalex.org/W2953132584","https://openalex.org/W2953384591","https://openalex.org/W2957824372","https://openalex.org/W2962843773","https://openalex.org/W2962915384","https://openalex.org/W2963019788","https://openalex.org/W2963028402","https://openalex.org/W2964121744","https://openalex.org/W4233060585","https://openalex.org/W4298090336","https://openalex.org/W4300456194","https://openalex.org/W4301246714","https://openalex.org/W6628746421","https://openalex.org/W6666041595","https://openalex.org/W6676297131","https://openalex.org/W6733938859","https://openalex.org/W6759166333"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W2891987081"],"abstract_inverted_index":{"Labeling":[0],"training":[1,31,203],"data":[2,71,172],"is":[3],"increasingly":[4],"the":[5,60,88,124,152,159,197],"largest":[6],"bottleneck":[7],"in":[8,127],"deploying":[9],"machine":[10,68],"learning":[11,69],"systems.":[12],"We":[13,73,122],"present":[14,74],"Snorkel,":[15],"a":[16,75,99],"first-of-its-kind":[17],"system":[18],"that":[19,38,139],"enables":[20],"users":[21,34],"to":[22,55,142,183],"train":[23],"state-of-":[24],"the-art":[25],"models":[26,106],"without":[27,53],"hand":[28,120],"labeling":[29,36,81],"any":[30],"data.":[32],"Instead,":[33],"write":[35],"functions":[37,82],"express":[39],"arbitrary":[40],"heuristics,":[41],"which":[42],"can":[43],"have":[44],"unknown":[45],"accuracies":[46],"and":[47,95,109,131,158,162,165,170,190],"correlations.":[48],"Snorkel":[49,178],"denoises":[50],"their":[51],"outputs":[52],"access":[54],"ground":[56],"truth":[57],"by":[58],"incorporating":[59],"first":[61],"end-to-end":[62],"implementation":[63],"of":[64,119,155,175,196,200],"our":[65,85],"recently":[66],"proposed":[67],"paradigm,":[70],"programming.":[72],"flexible":[76],"interface":[77],"layer":[78],"for":[79,135],"writing":[80],"based":[83],"on":[84,166],"experience":[86],"over":[87,186],"past":[89],"year":[90],"collaborating":[91],"with":[92,151],"companies,":[93],"agencies,":[94],"research":[96],"labs.":[97],"In":[98,148],"user":[100],"study,":[101],"subject":[102],"matter":[103],"experts":[104],"build":[105],"2.8\u00d7":[107],"faster":[108],"increase":[110],"predictive":[111,184,198],"performance":[112,185,199],"an":[113,133,193],"average":[114,181,194],"45.5%":[115],"versus":[116],"seven":[117],"hours":[118],"labeling.":[121],"study":[123],"modeling":[125],"tradeoffs":[126],"this":[128],"new":[129],"setting":[130],"propose":[132],"optimizer":[134],"automating":[136],"tradeoff":[137],"decisions":[138],"gives":[140],"up":[141],"1.8\u00d7":[143],"speedup":[144],"per":[145],"pipeline":[146],"execution.":[147],"two":[149],"collaborations,":[150],"U.S.":[153,160],"Department":[154],"Veterans":[156],"Affairs":[157],"Food":[161],"Drug":[163],"Administration,":[164],"four":[167],"open-source":[168],"text":[169],"image":[171],"sets":[173],"representative":[174],"other":[176],"deployments,":[177],"provides":[179],"132%":[180],"improvements":[182],"prior":[187],"heuristic":[188],"approaches":[189],"comes":[191],"within":[192],"3.60%":[195],"large":[201],"hand-curated":[202],"sets.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":74},{"year":2022,"cited_by_count":82},{"year":2021,"cited_by_count":191},{"year":2020,"cited_by_count":132},{"year":2019,"cited_by_count":109},{"year":2018,"cited_by_count":43}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2017-12-04T00:00:00"}