{"id":"https://openalex.org/W2949843842","doi":"https://doi.org/10.18653/v1/p19-1405","title":"Bayes Test of Precision, Recall, and F1 Measure for Comparison of Two Natural Language Processing Models","display_name":"Bayes Test of Precision, Recall, and F1 Measure for Comparison of Two Natural Language Processing Models","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949843842","doi":"https://doi.org/10.18653/v1/p19-1405","mag":"2949843842"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1405","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1405","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041138346","display_name":"Ruibo Wang","orcid":"https://orcid.org/0000-0002-9542-5081"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ruibo Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063383376","display_name":"Jihong Li","orcid":"https://orcid.org/0000-0002-5162-2737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihong Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041138346"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6017,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.9208905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4135","last_page":"4145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/estimator","display_name":"Estimator","score":0.571161687374115},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5215811133384705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.519504189491272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016031265258789},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4833638072013855},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.46788543462753296},{"id":"https://openalex.org/keywords/point-estimation","display_name":"Point estimation","score":0.4562356472015381},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.4551331102848053},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.42288511991500854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4043983519077301},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.362833172082901},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3201830983161926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21293318271636963},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1561627984046936}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.571161687374115},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5215811133384705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.519504189491272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016031265258789},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4833638072013855},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.46788543462753296},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.4562356472015381},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.4551331102848053},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.42288511991500854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4043983519077301},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.362833172082901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3201830983161926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21293318271636963},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1561627984046936},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1405","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1405","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W759515131","https://openalex.org/W1564649749","https://openalex.org/W1584308190","https://openalex.org/W1680392829","https://openalex.org/W1932968309","https://openalex.org/W1988995507","https://openalex.org/W2036705578","https://openalex.org/W2057399676","https://openalex.org/W2064675550","https://openalex.org/W2074698497","https://openalex.org/W2084784387","https://openalex.org/W2085770564","https://openalex.org/W2100954244","https://openalex.org/W2101937459","https://openalex.org/W2111216449","https://openalex.org/W2120199131","https://openalex.org/W2132812175","https://openalex.org/W2147880316","https://openalex.org/W2150706391","https://openalex.org/W2158143121","https://openalex.org/W2159805431","https://openalex.org/W2167277498","https://openalex.org/W2171421863","https://openalex.org/W2215432479","https://openalex.org/W2252040980","https://openalex.org/W2252264945","https://openalex.org/W2296283641","https://openalex.org/W2337811542","https://openalex.org/W2550196177","https://openalex.org/W2567649635","https://openalex.org/W2798935874","https://openalex.org/W2898547437","https://openalex.org/W2963313239","https://openalex.org/W2963583956"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W2075234375","https://openalex.org/W2037928913","https://openalex.org/W2006433632","https://openalex.org/W2032885221","https://openalex.org/W354308579","https://openalex.org/W1978405695","https://openalex.org/W1481984253"],"abstract_inverted_index":{"Direct":[0],"comparison":[1,51,94,154],"on":[2,21,73,176],"point":[3],"estimation":[4,66,144],"of":[5,14,38,57,67,117,125,134,145,173,179,209],"the":[6,43,55,99,123,126,131,153,171,174,177,180,189,204,207,210],"precision":[7],"(P),":[8],"recall":[9],"(R),":[10],"and":[11,28,63,70,110,113,120,137,139,148,160,183,203],"F1":[12,60,71,138],"measure":[13],"two":[15],"natural":[16],"language":[17],"processing":[18],"(NLP)":[19],"models":[20],"a":[22,36,39,74,86,156,162],"common":[23],"test":[24,167],"corpus":[25],"is":[26],"unreasonable":[27],"results":[29,205],"in":[30,46,92,101],"less":[31],"replicable":[32],"conclusions":[33],"due":[34],"to":[35,84,197],"lack":[37],"statistical":[40],"test.":[41,165,212],"However,":[42],"existing":[44,190],"t-tests":[45],"cross-validation":[47],"(CV)":[48],"for":[49],"model":[50,93],"are":[52,61,201],"inappropriate":[53],"because":[54,95],"distributions":[56,104,133,182],"P,":[58,68,118,135,146],"R,":[59,69,119,136,147],"skewed":[62],"an":[64,141],"interval":[65,143],"based":[72],"t-test":[75],"may":[76],"exceed":[77],"[0,1].":[78],"In":[79],"this":[80],"study,":[81],"we":[82,129,151],"propose":[83,161],"use":[85],"block-regularized":[87],"3\u00d72":[88,127],"CV":[89],"(3\u00d72":[90],"BCV)":[91],"it":[96],"could":[97,168],"regularize":[98],"difference":[100],"certain":[102],"frequency":[103],"over":[105],"linguistic":[106],"units":[107],"between":[108],"training":[109],"validation":[111],"sets":[112],"yield":[114],"stable":[115],"estimators":[116],"F1.":[121,149],"On":[122],"basis":[124,178],"BCV,":[128],"calibrate":[130],"posterior":[132,181],"derive":[140],"accurate":[142],"Furthermore,":[150],"formulate":[152],"into":[155],"hypothesis":[157],"testing":[158],"problem":[159],"novel":[163],"Bayes":[164,211],"The":[166],"directly":[169],"compute":[170],"probabilities":[172],"hypotheses":[175],"provide":[184],"more":[185],"informative":[186],"decisions":[187],"than":[188],"significance":[191],"t-tests.":[192],"Three":[193],"experiments":[194],"with":[195],"regard":[196],"NLP":[198],"chunking":[199],"tasks":[200],"conducted,":[202],"illustrate":[206],"validity":[208]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}