{"id":"https://openalex.org/W2890982112","doi":"https://doi.org/10.18653/v1/d18-1487","title":"Uncertainty-aware generative models for inferring document class prevalence","display_name":"Uncertainty-aware generative models for inferring document class prevalence","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890982112","doi":"https://doi.org/10.18653/v1/d18-1487","mag":"2890982112"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1487","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1487","pdf_url":"https://www.aclweb.org/anthology/D18-1487.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1487.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062069583","display_name":"Katherine A. Keith","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katherine Keith","raw_affiliation_strings":["College of Information and Computer Sciences University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023365550","display_name":"Brendan O\u2019Connor","orcid":"https://orcid.org/0000-0002-6857-1614"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan O\u2019Connor","raw_affiliation_strings":["College of Information and Computer Sciences University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062069583"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.3582,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.86382338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4575","last_page":"4585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"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":0.9965000152587891,"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/T10028","display_name":"Topic Modeling","score":0.9944999814033508,"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/T11309","display_name":"Music and Audio Processing","score":0.9940000176429749,"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/discriminative-model","display_name":"Discriminative model","score":0.8693219423294067},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7669430375099182},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7127832770347595},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6721940636634827},{"id":"https://openalex.org/keywords/point-estimation","display_name":"Point estimation","score":0.66629958152771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6283987164497375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6222228407859802},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6090357899665833},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5873884558677673},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5612960457801819},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4869135618209839},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.4797602593898773},{"id":"https://openalex.org/keywords/probabilistic-classification","display_name":"Probabilistic classification","score":0.4762972891330719},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4302205443382263},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3976382315158844},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.2984706163406372},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2981572151184082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2569580078125},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.11830994486808777}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8693219423294067},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7669430375099182},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7127832770347595},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6721940636634827},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.66629958152771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6283987164497375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6222228407859802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6090357899665833},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5873884558677673},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5612960457801819},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4869135618209839},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.4797602593898773},{"id":"https://openalex.org/C189119545","wikidata":"https://www.wikidata.org/wiki/Q5128022","display_name":"Probabilistic classification","level":4,"score":0.4762972891330719},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4302205443382263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3976382315158844},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.2984706163406372},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2981572151184082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2569580078125},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11830994486808777}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1487","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1487","pdf_url":"https://www.aclweb.org/anthology/D18-1487.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1487","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1487","pdf_url":"https://www.aclweb.org/anthology/D18-1487.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890982112.pdf","grobid_xml":"https://content.openalex.org/works/W2890982112.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W560287614","https://openalex.org/W1488030573","https://openalex.org/W1527373413","https://openalex.org/W1550206324","https://openalex.org/W1892539883","https://openalex.org/W1919365417","https://openalex.org/W1972047492","https://openalex.org/W1973193168","https://openalex.org/W1983599491","https://openalex.org/W2028138594","https://openalex.org/W2038411619","https://openalex.org/W2070996757","https://openalex.org/W2095734915","https://openalex.org/W2095881835","https://openalex.org/W2101234009","https://openalex.org/W2141253686","https://openalex.org/W2145853356","https://openalex.org/W2158243283","https://openalex.org/W2160044068","https://openalex.org/W2162514404","https://openalex.org/W2163614729","https://openalex.org/W2163900343","https://openalex.org/W2165279024","https://openalex.org/W2170081481","https://openalex.org/W2171060319","https://openalex.org/W2223083145","https://openalex.org/W2250243742","https://openalex.org/W2336481247","https://openalex.org/W2496945004","https://openalex.org/W2524454060","https://openalex.org/W2623107000","https://openalex.org/W2757560572","https://openalex.org/W2770820547","https://openalex.org/W2803277810","https://openalex.org/W2916132663","https://openalex.org/W2963042536","https://openalex.org/W2963577430","https://openalex.org/W2998048148","https://openalex.org/W3124321814","https://openalex.org/W3125379454","https://openalex.org/W4206375730","https://openalex.org/W4297804183"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W4394728283","https://openalex.org/W1493875009","https://openalex.org/W2105231718","https://openalex.org/W4388844349","https://openalex.org/W4226099195"],"abstract_inverted_index":{"Prevalence":[0],"estimation":[1],"is":[2,135],"the":[3,7,19,55,78,142],"task":[4],"of":[5,10,12,21,82],"inferring":[6],"relative":[8],"frequency":[9],"classes":[11],"unlabeled":[13],"examples":[14],"in":[15,52,86,141],"a":[16,22,68,98],"group-for":[17],"example,":[18],"proportion":[20],"document":[23],"collection":[24],"with":[25],"positive":[26],"sentiment.":[27],"Previous":[28],"work":[29],"has":[30],"focused":[31],"on":[32],"aggregating":[33],"and":[34,76,80,116,134,147],"adjusting":[35],"discriminative":[36,93],"individual":[37],"classifiers":[38],"to":[39,49,73,113,139],"obtain":[40],"prevalence":[41,57,74,83],"point":[42],"estimates.":[43],"But":[44],"imperfect":[45],"classifier":[46,94],"accuracy":[47],"ought":[48],"be":[50,96,111],"reflected":[51],"uncertainty":[53],"over":[54],"predicted":[56],"for":[58],"scientifically":[59],"valid":[60],"inference.":[61,120],"In":[62],"this":[63],"work,":[64],"we":[65,88,122],"present":[66],"(1)":[67],"generative":[69,99],"probabilistic":[70],"modeling":[71],"approach":[72,125],"estimation,":[75],"(2)":[77],"construction":[79],"evaluation":[81],"confidence":[84,128],"intervals;":[85],"particular,":[87],"demonstrate":[89,123],"that":[90],"an":[91,104,132],"off-theshelf":[92],"can":[95,110],"given":[97],"re-interpretation,":[100],"by":[101],"backing":[102],"out":[103],"implicit":[105],"individual-level":[106],"likelihood":[107],"function,":[108],"which":[109],"used":[112],"conduct":[114],"fast":[115],"simple":[117],"group-level":[118],"Bayesian":[119],"Empirically,":[121],"our":[124],"provides":[126],"better":[127],"interval":[129],"coverage":[130],"than":[131],"alternative,":[133],"dramatically":[136],"more":[137],"robust":[138],"shifts":[140],"class":[143],"prior":[144],"between":[145],"training":[146],"testing.":[148],"1":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}