{"id":"https://openalex.org/W2772794423","doi":"https://doi.org/10.1162/coli_r_00310","title":"Bayesian Analysis in Natural Language Processing","display_name":"Bayesian Analysis in Natural Language Processing","publication_year":2017,"publication_date":"2017-12-14","ids":{"openalex":"https://openalex.org/W2772794423","doi":"https://doi.org/10.1162/coli_r_00310","mag":"2772794423"},"language":"en","primary_location":{"id":"doi:10.1162/coli_r_00310","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00310","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_r_00310","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_r_00310","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070418792","display_name":"Kevin Duh","orcid":"https://orcid.org/0000-0001-8107-4383"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin Duh","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070418792"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.8322,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8146493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"44","issue":"1","first_page":"187","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9968000054359436,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9948999881744385,"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":0.7618990540504456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7156167030334473},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5993924140930176},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5269699096679688},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5140367746353149},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4866848587989807},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.48233601450920105},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.48054009675979614},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4596860110759735},{"id":"https://openalex.org/keywords/coreference","display_name":"Coreference","score":0.45615828037261963},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4133416414260864},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.23226559162139893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618990540504456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7156167030334473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5993924140930176},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5269699096679688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5140367746353149},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4866848587989807},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.48233601450920105},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.48054009675979614},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4596860110759735},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.45615828037261963},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4133416414260864},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.23226559162139893},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_r_00310","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00310","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_r_00310","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:033267d116ed45ec8f01d83f42645680","is_oa":false,"landing_page_url":"https://doaj.org/article/033267d116ed45ec8f01d83f42645680","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 44, Iss 1, Pp 187-189 (2018)","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:803113826abf4d9f9c39f0e30ed01f41","is_oa":false,"landing_page_url":"https://doaj.org/article/803113826abf4d9f9c39f0e30ed01f41","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 44, Iss 1 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_r_00310","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00310","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_r_00310","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2772794423.pdf","grobid_xml":"https://content.openalex.org/works/W2772794423.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W2084499688","https://openalex.org/W2116211107","https://openalex.org/W2117126688","https://openalex.org/W2126270798","https://openalex.org/W2126377586","https://openalex.org/W2147706904"],"related_works":["https://openalex.org/W1872130062","https://openalex.org/W2464738873","https://openalex.org/W2293457016","https://openalex.org/W159132833","https://openalex.org/W2977842567","https://openalex.org/W2187475485","https://openalex.org/W3168957480","https://openalex.org/W87581401","https://openalex.org/W2502722637","https://openalex.org/W3198474835"],"abstract_inverted_index":{"Bayesian":[0,20,126,173,229,284,312,329,337,389,432,532,615,631,674,697,736,755],"techniques":[1,127,313,338,390,616,756],"are":[2,34,224,288,339,409,511,516],"useful":[3],"tools":[4],"for":[5,46,81,111,324,332,343,349,413,537,633,685],"modeling":[6,189,327],"a":[7,43,47,64,179,249,260,297,464,473,561,597,600,605,653,668,681,686,689,725],"wide":[8],"range":[9],"of":[10,84,125,197,213,256,263,278,440,477,546,557,564],"data":[11,27,448],"and":[12,90,97,158,221,234,254,265,276,285,305,328,422,436,450,489,500,582,587,604,629,703,713],"phenomena.":[13],"Natural":[14,677],"language":[15,130,192],"is":[16,176,184,216,259,377,385,393,522,553,680],"no":[17],"exception.":[18],"The":[19,210,281],"approach":[21,86],"works":[22],"as":[23,114,201,272,426,596,718,724],"follows:1.":[24],"Model":[25],"the":[26,59,78,82,195,214,219,239,294,303,308,353,362,405,415,418,427,438,441,447,451,455,471,497,501,543,566,570,575,580,590,610,662,701,715,730],"x":[28],"probabilistically":[29],"with":[30,187,316,388,549,778],"p(x|\u03b8),":[31],"where":[32,352],"\u03b8":[33,62],"some":[35,52,786],"unknown":[36,53],"parameters.":[37,101],"For":[38],"example,":[39,414],"this":[40,246,657,711,747],"could":[41],"be":[42,105,463,594,618,722,741],"generative":[44],"story":[45],"sentence":[48],"x,":[49],"based":[50],"on":[51,302,307,531,627,644,735],"context-free":[54,635],"grammar":[55,621,648],"parameters":[56,547],"\u03b8.2.":[57],"Represent":[58],"uncertainty":[60,99],"about":[61,374,696],"by":[63,670,771],"prior":[65,95,452,598],"distribution":[66,80,457],"p(\u03b8).3.":[67],"Given":[68],"data,":[69],"apply":[70],"Bayes":[71],"theorem":[72],"p(\u03b8|x)":[73,458],"\u221d":[74,459],"p(x|\u03b8)p(\u03b8)":[75],"to":[76,93,107,117,172,217,226,235,358,381,453,620,665,693,707,740,753],"find":[77,359],"posterior":[79,456,474],"quantities":[83],"interest.This":[85],"enables":[87],"an":[88,115,167,538,554,641],"elegant":[89],"unified":[91],"way":[92],"incorporate":[94],"knowledge":[96,705],"manage":[98],"over":[100],"It":[102,175,267,625,699,720],"can":[103,462,593,617,721],"also":[104],"used":[106,342,395,595],"provide":[108],"capacity":[109],"control":[110],"complex":[112],"models":[113,535,622,632],"alternative":[116],"smoothing.":[118],"There":[119],"have":[120,660,783],"been":[121],"many":[122,731],"successful":[123],"applications":[124,646],"in":[128,190,232,238,314,346,396,411,434,513,518,599,623,676,710,758],"natural":[129,191],"processing":[131],"(NLP).":[132],"Some":[133],"examples":[134],"include:":[135],"word":[136],"segmentation":[137],"(Goldwater":[138],"et":[139,144,162],"al.":[140,145,163],"2009),":[141],"syntax":[142],"(Johnson":[143],"2007),":[146,157],"morphology":[147],"(Snyder":[148],"&":[149,155,203,207],"Barzilay":[150],"2008),":[151],"coreference":[152],"resolution":[153],"(Haghighi":[154],"Klein":[156],"machine":[159],"translation":[160],"(Blunsom":[161],"2009).Cohen\u2019s":[164],"book":[165,215,295,658,748,781],"provides":[166],"accessible":[168],"yet":[169],"in-depth":[170],"introduction":[171,727],"techniques.":[174,698],"aimed":[177],"at":[178,194],"researcher":[180,687],"or":[181,688],"student":[182,690],"who":[183,655,691],"already":[185],"familiar":[186],"statistical":[188],"(i.e.,":[193],"level":[196],"introductory":[198],"books":[199],"such":[200,271,425,667],"Manning":[202],"Sch\u00fctze":[204],"[1999],":[205],"Jurafsky":[206],"Martin":[208],"[2009]).":[209],"stated":[211],"goal":[212],"\u201ccover":[218],"methods":[220],"algorithms":[222],"that":[223,371,378,408,510,728],"needed":[225,706],"fluently":[227],"read":[228],"learning":[230],"papers":[231,709],"NLP":[233,315,347,514],"do":[236,666],"research":[237,515],"area.\u201d":[240],"I":[241,372,637,651,745,750,760],"believe":[242],"Cohen":[243,559],"successfully":[244],"achieves":[245],"goal,":[247],"striking":[248],"nice":[250],"balance":[251],"between":[252,283,383],"breadth":[253],"depth":[255],"material.Chapter":[257],"1":[258],"brief":[261],"review":[262],"probability":[264],"statistics.":[266],"covers":[268,481,700],"prerequisite":[269],"concepts":[270],"independence,":[273,275],"conditional":[274],"exchangeability":[277],"random":[279],"variables.":[280],"differences":[282],"frequentist":[286],"philosophies":[287],"discussed,":[289],"albeit":[290],"briefly.":[291],"In":[292,505],"general,":[293],"maintains":[296],"pragmatic":[298],"approach,":[299],"focusing":[300],"more":[301,695,742],"mathematics":[304,568],"less":[306],"philosophy.Chapter":[309],"2":[310],"motivates":[311],"two":[317],"distinct":[318],"examples:":[319],"latent":[320],"Dirichlet":[321,416,571,576,591],"allocation":[322],"(LDA)":[323],"unsupervised":[325,344],"topic":[326,607],"linear":[330],"regression":[331],"supervised":[333,363],"text":[334],"analytics.":[335],"Although":[336],"most":[340],"often":[341],"problems":[345,351],"(e.g.,":[348],"addressing":[350],"Expectation-Maximization":[354],"[EM]":[355],"algorithm":[356,508],"fails":[357],"good":[360,682],"solutions),":[361],"example":[364,521],"demonstrates":[365,613],"their":[366],"broader":[367],"applicability.":[368],"One":[369],"aspect":[370],"appreciate":[373],"Cohen\u2019s":[375,673,780],"exposition":[376],"he":[379],"strives":[380],"distinguish":[382],"what":[384,392],"technically":[386],"feasible":[387],"vs.":[391],"frequently":[394],"research.":[397,558],"This":[398,461,552],"helps":[399],"avoid":[400],"potential":[401],"misconceptions.Chapter":[402],"3":[403],"describes":[404,494,579],"priors":[406,424],"p(\u03b8)":[407],"common":[410],"NLP:":[412],"distribution,":[417,421],"logistic":[419],"normal":[420],"non-informative":[423],"Jeffreys":[428],"prior.Chapters":[429],"4\u20136":[430],"explain":[431],"inference":[433],"detail":[435],"form":[437],"core":[439],"book.":[442],"How":[443],"does":[444,560],"one":[445],"combine":[446],"likelihood":[449],"compute":[454],"p(x|\u03b8)p(\u03b8)?":[460],"computationally":[465],"difficult":[466],"problem.":[467],"Chapter":[468,479,492],"4":[469],"discusses":[470],"maximum":[472],"(MAP)":[475],"estimation":[476],"p(\u03b8|x).":[478],"5":[480],"sampling":[482,525],"methods,":[483],"particularly":[484],"Gibbs":[485,524],"sampling,":[486,488],"Metropolis-Hastings":[487],"slice":[490],"sampling.":[491],"6":[493],"variational":[495,502],"inference,":[496],"mean-field":[498],"approximation,":[499],"EM":[503],"algorithm.":[504],"each":[506],"chapter,":[507,612],"variants":[509],"popular":[512],"discussed":[517],"detail.":[519],"An":[520],"blocked":[523],"using":[526],"dynamic":[527],"programming.Chapter":[528],"7":[529],"focuses":[530,626],"nonparameterics.":[533],"These":[534],"allow":[536],"infinite-dimensional":[539],"parameter":[540],"space,":[541],"but":[542],"actual":[544],"number":[545],"grows":[548],"sample":[550],"size.":[551],"active":[555],"field":[556],"laudable":[562],"job":[563],"explaining":[565],"basic":[567],"behind":[569],"process,":[572],"which":[573,738],"generalizes":[574],"distribution.":[577],"He":[578],"stick-breaking":[581],"Chinese":[583],"Restaurant":[584],"Process":[585],"viewpoints,":[586],"shows":[588],"how":[589,614],"process":[592],"nonparametric":[601],"mixture":[602],"model":[603],"hierarchical":[606],"model.Chapter":[608],"8,":[609],"final":[611],"applied":[619],"NLP.":[624],"parametric":[628],"non-parameteric":[630],"probabilistic":[634],"grammars.":[636],"wished":[638],"there":[639],"was":[640],"additional":[642],"chapter":[643],"other":[645],"besides":[647],"models.":[649],"However,":[650],"think":[652],"reader":[654],"completes":[656],"would":[659],"gained":[661],"technical":[663],"background":[664],"survey":[669],"themselves.In":[671],"summary,":[672],"Analysis":[675],"Language":[678],"Processing":[679],"starting":[683],"point":[684],"wishes":[692],"learn":[694,754],"necessary":[702],"sufficient":[704],"understand":[708],"area,":[712],"leaves":[714],"remaining":[716],"details":[717],"references.":[719],"viewed":[723],"concise":[726],"complements":[729],"excellent":[732],"statistics":[733,766],"textbooks":[734],"techniques,":[737],"tend":[739],"detailed.I":[743],"wish":[744],"had":[746],"when":[749],"first":[751],"started":[752],"back":[757],"2009.":[759],"recall":[761],"struggling":[762],"through":[763],"several":[764],"advanced":[765],"textbooks,":[767],"before":[768],"being":[769],"rescued":[770],"Kevin":[772],"Knight\u2019s":[773],"classic":[774],"workbook,":[775],"\u201cBayesian":[776],"Inference":[777],"Tears.\u201d1":[779],"might":[782],"saved":[784],"me":[785],"Kleenex.":[787]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}