{"id":"https://openalex.org/W2131924950","doi":"https://doi.org/10.5555/1953048.2021075","title":"Producing Power-Law Distributions and Damping Word Frequencies with Two-Stage Language Models","display_name":"Producing Power-Law Distributions and Damping Word Frequencies with Two-Stage Language Models","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2131924950","doi":"https://doi.org/10.5555/1953048.2021075","mag":"2131924950"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:publications/7a14bdb6-7ff2-4f2b-a1a7-4e643793170f","is_oa":false,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/7a14bdb6-7ff2-4f2b-a1a7-4e643793170f","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Goldwater, S, Griffiths, T & Johnson, M 2011, 'Producing power-law distributions and damping word frequencies with two-stage language models', Journal of Machine Learning Research, vol. 12, pp. 2335-2382.","raw_type":"info:eu-repo/semantics/article"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f175d3a6-0256-45b2-a807-affadc588aed","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics"],"raw_orcid":"https://orcid.org/0000-0002-7298-0947","affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077079119","display_name":"Thomas L. Griffiths","orcid":"https://orcid.org/0000-0002-5138-7255"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas L. Griffiths","raw_affiliation_strings":["School of Psychological Science"],"raw_orcid":"https://orcid.org/0000-0002-5138-7255","affiliations":[{"raw_affiliation_string":"School of Psychological Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034461489","display_name":"Mark Johnson","orcid":"https://orcid.org/0000-0003-4809-8441"},"institutions":[{"id":"https://openalex.org/I4210141709","display_name":"ARC Centre of Excellence in Cognition and its Disorders","ror":"https://ror.org/044b7p696","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1337719021","https://openalex.org/I2801453606","https://openalex.org/I4210132349","https://openalex.org/I4210141709","https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mark Johnson","raw_affiliation_strings":["ARC Centre of Excellence in Cognition and its Disorders (CCD)"],"raw_orcid":"https://orcid.org/0000-0003-4809-8441","affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence in Cognition and its Disorders (CCD)","institution_ids":["https://openalex.org/I4210141709"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4903,"has_fulltext":true,"cited_by_count":73,"citation_normalized_percentile":{"value":0.97973155,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"12","issue":"68","first_page":"2335","last_page":"2382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T12090","display_name":"Language and cultural evolution","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6094898581504822},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5572088956832886},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5116946697235107},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4631336033344269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4543328881263733},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.4472256898880005},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4434102475643158},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44114136695861816},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4161539673805237},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.337232768535614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.302347868680954},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.20644155144691467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6094898581504822},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5572088956832886},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5116946697235107},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4631336033344269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4543328881263733},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.4472256898880005},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4434102475643158},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44114136695861816},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4161539673805237},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.337232768535614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.302347868680954},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.20644155144691467},{"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},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:pure.atira.dk:publications/7a14bdb6-7ff2-4f2b-a1a7-4e643793170f","is_oa":false,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/7a14bdb6-7ff2-4f2b-a1a7-4e643793170f","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Goldwater, S, Griffiths, T & Johnson, M 2011, 'Producing power-law distributions and damping word frequencies with two-stage language models', Journal of Machine Learning Research, vol. 12, pp. 2335-2382.","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f175d3a6-0256-45b2-a807-affadc588aed","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f175d3a6-0256-45b2-a807-affadc588aed","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Goldwater, S, Griffiths, T L & Johnson, M 2011, 'Producing power-law distributions and damping word frequencies with two-stage language models', Journal of Machine Learning Research, vol. 12(Jul), pp. 2335-2382. < http://www.jmlr.org/papers/volume12/goldwater11a/goldwater11a.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f175d3a6-0256-45b2-a807-affadc588aed","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/f175d3a6-0256-45b2-a807-affadc588aed","pdf_url":"https://www.research.ed.ac.uk/en/publications/f175d3a6-0256-45b2-a807-affadc588aed","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Goldwater, S, Griffiths, T L & Johnson, M 2011, 'Producing power-law distributions and damping word frequencies with two-stage language models', Journal of Machine Learning Research, vol. 12(Jul), pp. 2335-2382. < http://www.jmlr.org/papers/volume12/goldwater11a/goldwater11a.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:2131924950","is_oa":false,"landing_page_url":"http://cocosci.berkeley.edu/tom/papers/goldwater11a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f175d3a6-0256-45b2-a807-affadc588aed","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f175d3a6-0256-45b2-a807-affadc588aed","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Goldwater, S, Griffiths, T L & Johnson, M 2011, 'Producing power-law distributions and damping word frequencies with two-stage language models', Journal of Machine Learning Research, vol. 12(Jul), pp. 2335-2382. < http://www.jmlr.org/papers/volume12/goldwater11a/goldwater11a.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W82218792","https://openalex.org/W201532657","https://openalex.org/W263845233","https://openalex.org/W274041255","https://openalex.org/W1479758177","https://openalex.org/W1491115232","https://openalex.org/W1517266559","https://openalex.org/W1540302538","https://openalex.org/W1551893515","https://openalex.org/W1579929927","https://openalex.org/W1632114991","https://openalex.org/W1660390307","https://openalex.org/W1880262756","https://openalex.org/W1892363745","https://openalex.org/W1934041838","https://openalex.org/W1967687583","https://openalex.org/W1967770672","https://openalex.org/W1969608442","https://openalex.org/W1970887833","https://openalex.org/W1975992139","https://openalex.org/W1978394996","https://openalex.org/W1993803315","https://openalex.org/W1995991622","https://openalex.org/W2001082470","https://openalex.org/W2004353685","https://openalex.org/W2005902041","https://openalex.org/W2025653016","https://openalex.org/W2033937535","https://openalex.org/W2036671379","https://openalex.org/W2042143122","https://openalex.org/W2047603832","https://openalex.org/W2053218206","https://openalex.org/W2061430448","https://openalex.org/W2069429561","https://openalex.org/W2069931267","https://openalex.org/W2070554026","https://openalex.org/W2073610029","https://openalex.org/W2074546930","https://openalex.org/W2075201173","https://openalex.org/W2077460999","https://openalex.org/W2080972498","https://openalex.org/W2086426947","https://openalex.org/W2087309226","https://openalex.org/W2089484716","https://openalex.org/W2091797506","https://openalex.org/W2093254167","https://openalex.org/W2100881784","https://openalex.org/W2101711363","https://openalex.org/W2103731025","https://openalex.org/W2111568643","https://openalex.org/W2113788796","https://openalex.org/W2115529864","https://openalex.org/W2116137244","https://openalex.org/W2116211107","https://openalex.org/W2116361377","https://openalex.org/W2116850456","https://openalex.org/W2117126688","https://openalex.org/W2120636621","https://openalex.org/W2122228338","https://openalex.org/W2123301651","https://openalex.org/W2126377586","https://openalex.org/W2126449874","https://openalex.org/W2126953647","https://openalex.org/W2130416410","https://openalex.org/W2131287128","https://openalex.org/W2132827946","https://openalex.org/W2132957691","https://openalex.org/W2135631383","https://openalex.org/W2150507172","https://openalex.org/W2152600988","https://openalex.org/W2154099718","https://openalex.org/W2157381218","https://openalex.org/W2157874452","https://openalex.org/W2158190429","https://openalex.org/W2158195707","https://openalex.org/W2158266063","https://openalex.org/W2159399018","https://openalex.org/W2163131995","https://openalex.org/W2166451556","https://openalex.org/W2172135926","https://openalex.org/W2201609126","https://openalex.org/W2952343510","https://openalex.org/W3145738572"],"related_works":["https://openalex.org/W2154099718","https://openalex.org/W2087309226","https://openalex.org/W2117126688","https://openalex.org/W2064675550","https://openalex.org/W1880262756","https://openalex.org/W2164151151","https://openalex.org/W2158266063","https://openalex.org/W2159399018","https://openalex.org/W2069429561","https://openalex.org/W2036671379","https://openalex.org/W1934041838","https://openalex.org/W2165814974","https://openalex.org/W2158195707","https://openalex.org/W2005902041","https://openalex.org/W179875071","https://openalex.org/W2134237567","https://openalex.org/W2126449874","https://openalex.org/W1631260214","https://openalex.org/W1574901103","https://openalex.org/W1532325895"],"abstract_inverted_index":{"Standard":[0],"statistical":[1,32],"models":[2,33,42],"of":[3,9,14,23,67,99,149,166,172,179,185],"language":[4,174],"fail":[5],"to":[6,70,75,127],"capture":[7],"one":[8],"the":[10,17,21,49,58,61,64,86,90,116,155,164,177],"most":[11],"striking":[12],"properties":[13],"natural":[15,76,173],"languages:":[16],"power-law":[18,129],"distribution":[19],"in":[20,124,169],"frequencies":[22,66,168],"word":[24,65,132],"tokens.":[25],"We":[26,78,102,134],"present":[27],"a":[28,72,180],"framework":[29,126],"for":[30,182],"developing":[31],"that":[34,80,136],"can":[35,51,93,119],"generically":[36],"produce":[37,128],"power":[38],"laws,":[39],"breaking":[40],"generative":[41],"into":[43],"two":[44,81,104],"stages.":[45],"The":[46],"first":[47],"stage,":[48,60],"generator,":[50],"be":[52,94,120],"any":[53],"standard":[54],"probabilistic":[55],"model,":[56],"while":[57],"second":[59],"adaptor,":[62],"transforms":[63],"this":[68],"model":[69,88,181],"provide":[71],"closer":[73],"match":[74],"language.":[77],"show":[79,135],"commonly":[82],"used":[83,121],"Bayesian":[84],"models,":[85],"Dirichlet-multinomial":[87],"and":[89,110,175],"Dirichlet":[91],"process,":[92],"viewed":[95],"as":[96,122,160],"special":[97],"cases":[98],"our":[100,125],"framework.":[101],"discuss":[103],"stochastic":[105],"processes---the":[106],"Chinese":[107,157],"restaurant":[108,158],"process":[109,159],"its":[111],"two-parameter":[112],"generalization":[113],"based":[114,143],"on":[115,144],"Pitman-Yor":[117,156],"process---that":[118],"adaptors":[123,138],"distributions":[130],"over":[131],"frequencies.":[133,151],"these":[137],"justify":[139],"common":[140],"estimation":[141],"procedures":[142],"logarithmic":[145],"or":[146],"inverse-power":[147],"transformations":[148],"empirical":[150],"In":[152],"addition,":[153],"taking":[154],"an":[161],"adaptor":[162],"justifies":[163],"appearance":[165],"type":[167],"formal":[170],"analyses":[171],"improves":[176],"performance":[178],"unsupervised":[183],"learning":[184],"morphology.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}