{"id":"https://openalex.org/W2132957691","doi":"https://doi.org/10.1017/s1351324900000218","title":"A hierarchical Dirichlet language model","display_name":"A hierarchical Dirichlet language model","publication_year":1995,"publication_date":"1995-09-01","ids":{"openalex":"https://openalex.org/W2132957691","doi":"https://doi.org/10.1017/s1351324900000218","mag":"2132957691"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324900000218","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324900000218","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053054196","display_name":"David Mackay","orcid":"https://orcid.org/0000-0002-5271-2996"},"institutions":[{"id":"https://openalex.org/I4210107224","display_name":"Cavendish Hospital","ror":"https://ror.org/01gnx5040","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210107224","https://openalex.org/I4210121323"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"David J. C. MacKay","raw_affiliation_strings":["Cavendish LaboratoryCambridge CB3 0HE, UK","Cavendish Laboratory Cambridge CB3 0HE, UK"],"affiliations":[{"raw_affiliation_string":"Cavendish LaboratoryCambridge CB3 0HE, UK","institution_ids":["https://openalex.org/I4210107224"]},{"raw_affiliation_string":"Cavendish Laboratory Cambridge CB3 0HE, UK","institution_ids":["https://openalex.org/I4210107224"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003457359","display_name":"Linda C. Bauman Peto","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Linda C. Bauman Peto","raw_affiliation_strings":["Department of Computer ScienceUniversity of Toronto, Canada","Department of Computer Science University of Toronto, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer ScienceUniversity of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science University of Toronto, Canada#TAB#","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053054196"],"corresponding_institution_ids":["https://openalex.org/I4210107224"],"apc_list":null,"apc_paid":null,"fwci":5.882,"has_fulltext":false,"cited_by_count":275,"citation_normalized_percentile":{"value":0.96099342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"1","issue":"3","first_page":"289","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9987000226974487,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9987000226974487,"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":0.9926999807357788,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9747999906539917,"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/smoothing","display_name":"Smoothing","score":0.8625261187553406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8604514598846436},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7282850742340088},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7029666900634766},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.5733646750450134},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.571979284286499},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5093725919723511},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4983222484588623},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.475897878408432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45170557498931885},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4461734890937805},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4338741898536682},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.40500903129577637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36891913414001465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36202025413513184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34312570095062256},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21922162175178528},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.19021597504615784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09602734446525574}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.8625261187553406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8604514598846436},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7282850742340088},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7029666900634766},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.5733646750450134},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.571979284286499},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5093725919723511},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4983222484588623},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.475897878408432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45170557498931885},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4461734890937805},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4338741898536682},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.40500903129577637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36891913414001465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36202025413513184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34312570095062256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21922162175178528},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.19021597504615784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09602734446525574},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324900000218","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324900000218","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.371.2042","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.371.2042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ftp.cs.toronto.edu/pub/gh/MacKay+Peto-1995.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.50.1464","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.50.1464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/afs/cs.cmu.edu/user/jlaff/www/local/handouts/lang4.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"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":28,"referenced_works":["https://openalex.org/W29489373","https://openalex.org/W147878758","https://openalex.org/W172742023","https://openalex.org/W179344782","https://openalex.org/W183862812","https://openalex.org/W647344759","https://openalex.org/W1489181569","https://openalex.org/W1507086444","https://openalex.org/W1589097414","https://openalex.org/W1591751678","https://openalex.org/W1597533204","https://openalex.org/W1966812932","https://openalex.org/W1967687583","https://openalex.org/W1974413746","https://openalex.org/W1978861152","https://openalex.org/W2006969979","https://openalex.org/W2025130480","https://openalex.org/W2026915078","https://openalex.org/W2134237567","https://openalex.org/W2134696506","https://openalex.org/W2149741699","https://openalex.org/W2159782014","https://openalex.org/W2170120409","https://openalex.org/W2611071497","https://openalex.org/W4308067218","https://openalex.org/W6607493073","https://openalex.org/W6652311901","https://openalex.org/W6682264535"],"related_works":["https://openalex.org/W2048766621","https://openalex.org/W2803512450","https://openalex.org/W2097627380","https://openalex.org/W2939843948","https://openalex.org/W2053909857","https://openalex.org/W2031284124","https://openalex.org/W2250993361","https://openalex.org/W2116506662","https://openalex.org/W2537397241","https://openalex.org/W2761041348"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"discuss":[2],"a":[3,34,82],"hierarchical":[4,97],"probabilistic":[5,35],"model":[6,98],"whose":[7],"predictions":[8],"are":[9,52],"similar":[10],"to":[11,55,90],"those":[12],"of":[13,24,37,49,62],"the":[14,60,96],"popular":[15],"language":[16,45],"modelling":[17,61],"procedure":[18],"known":[19],"as":[20,59],"\u2018smoothing\u2019.":[21],"A":[22],"number":[23],"interesting":[25],"differences":[26],"from":[27,33],"smoothing":[28,80],"emerge.":[29],"The":[30,47,74,87],"insights":[31],"gained":[32],"view":[36],"this":[38,50],"problem":[39],"point":[40],"towards":[41],"new":[42,75],"directions":[43],"for":[44],"modelling.":[46],"ideas":[48],"paper":[51],"also":[53],"applicable":[54],"other":[56],"problems":[57],"such":[58],"triphomes":[63],"in":[64,71],"speech,":[65],"and":[66,68],"DNA":[67],"protein":[69],"sequences":[70],"molecular":[72],"biology.":[73],"algorithm":[76],"is":[77],"compared":[78],"with":[79,95],"on":[81],"two":[83],"million":[84],"word":[85],"corpus.":[86],"methods":[88],"prove":[89],"be":[91],"about":[92],"equally":[93],"accurate,":[94],"using":[99],"fewer":[100],"computational":[101],"resources.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":23}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}