{"id":"https://openalex.org/W2112476714","doi":"https://doi.org/10.1109/icassp.2011.5946754","title":"Bayesian reinforcement learning for POMDP-based dialogue systems","display_name":"Bayesian reinforcement learning for POMDP-based dialogue systems","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2112476714","doi":"https://doi.org/10.1109/icassp.2011.5946754","mag":"2112476714"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.82308/1694","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037959209","display_name":"Shaowei Png","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"ShaoWei Png","raw_affiliation_strings":["School of Computer Science, McGill University, Montreal, QUE, Canada","McGill University, School of Computer Science, Montreal, QC H3A 1A8, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University, Montreal, QUE, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, School of Computer Science, Montreal, QC H3A 1A8, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["School of Computer Science, McGill University, Montreal, QUE, Canada","McGill University, School of Computer Science, Montreal, QC H3A 1A8, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University, Montreal, QUE, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, School of Computer Science, Montreal, QC H3A 1A8, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":2.9675,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92317765,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2156","last_page":"2159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9988999962806702,"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":0.9976999759674072,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8418270349502563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8231521844863892},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7496837973594666},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7230566740036011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6456387042999268},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5467913150787354},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5321599245071411},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4765263795852661},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4634542167186737},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.07560703158378601}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8418270349502563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231521844863892},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7496837973594666},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7230566740036011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6456387042999268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5467913150787354},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5321599245071411},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4765263795852661},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4634542167186737},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.07560703158378601},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2011.5946754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:doi:10.82308/1694","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14905/97554","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"raw_type":"https://vocabularies.coar-repositories.org/resource_types/c_46ec/"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.421.1987","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.421.1987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~jpineau/files/png-icassp11.pdf","raw_type":"text"},{"id":"pmh:oai:collectionscanada.gc.ca:QMM.104830","is_oa":false,"landing_page_url":"http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=104830","pdf_url":null,"source":{"id":"https://openalex.org/S4306402307","display_name":"Library and Archives Canada (Government of Canada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802286613","host_organization_name":"Government of Canada","host_organization_lineage":["https://openalex.org/I2802286613"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Electronic Thesis or Dissertation"},{"id":"pmh:oai:escholarship.mcgill.ca:8910jz56d","is_oa":false,"landing_page_url":"https://escholarship.mcgill.ca/concern/theses/8910jz56d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401568","display_name":"eScholarship@McGill (McGill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5023651","host_organization_name":"McGill University","host_organization_lineage":["https://openalex.org/I5023651"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"doi:10.82308/1694","is_oa":true,"landing_page_url":"https://doi.org/10.82308/1694","pdf_url":null,"source":{"id":"https://openalex.org/S7407060097","display_name":"McGill-DEV","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"}],"best_oa_location":{"id":"doi:10.82308/1694","is_oa":true,"landing_page_url":"https://doi.org/10.82308/1694","pdf_url":null,"source":{"id":"https://openalex.org/S7407060097","display_name":"McGill-DEV","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W27627492","https://openalex.org/W36013382","https://openalex.org/W62710299","https://openalex.org/W1484113995","https://openalex.org/W1496855202","https://openalex.org/W1526144783","https://openalex.org/W1532688806","https://openalex.org/W1539216098","https://openalex.org/W1580557482","https://openalex.org/W1581952794","https://openalex.org/W1600735390","https://openalex.org/W1622397659","https://openalex.org/W1681299129","https://openalex.org/W1941785850","https://openalex.org/W2007221309","https://openalex.org/W2011418219","https://openalex.org/W2028145673","https://openalex.org/W2034725503","https://openalex.org/W2076082451","https://openalex.org/W2098432798","https://openalex.org/W2099430963","https://openalex.org/W2099873296","https://openalex.org/W2101421095","https://openalex.org/W2107282196","https://openalex.org/W2112259378","https://openalex.org/W2116459397","https://openalex.org/W2117989772","https://openalex.org/W2119567691","https://openalex.org/W2133434946","https://openalex.org/W2134802714","https://openalex.org/W2135681007","https://openalex.org/W2141839844","https://openalex.org/W2144794447","https://openalex.org/W2144913588","https://openalex.org/W2146092999","https://openalex.org/W2151814822","https://openalex.org/W2160219061","https://openalex.org/W2160422981","https://openalex.org/W2167353639","https://openalex.org/W2168359464","https://openalex.org/W2168490009","https://openalex.org/W2169294731","https://openalex.org/W2171084228","https://openalex.org/W2184461682","https://openalex.org/W2202767678","https://openalex.org/W2294827575","https://openalex.org/W2438667436","https://openalex.org/W3016548437","https://openalex.org/W3099293669","https://openalex.org/W3150017941","https://openalex.org/W6602539159","https://openalex.org/W6628758712","https://openalex.org/W6629614444","https://openalex.org/W6631864160","https://openalex.org/W6637231811","https://openalex.org/W6679977494","https://openalex.org/W6681472862"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W4294565801","https://openalex.org/W2142306706"],"abstract_inverted_index":{"Spoken":[0],"dialogue":[1,29,78,118],"systems":[2,13],"are":[3,36,108],"gaining":[4],"popularity":[5],"with":[6],"improvements":[7,21],"in":[8,22],"speech":[9],"recognition":[10],"technologies.":[11],"Dialogue":[12],"can":[14,40],"be":[15,41],"modeled":[16],"effectively":[17],"using":[18,101],"POMDPs,":[19],"achieving":[20],"robustness.":[23],"However,":[24,58],"past":[25],"research":[26],"on":[27,114],"POMDPs-based":[28],"system":[30,119],"assumes":[31],"that":[32,85],"the":[33,61,65,92],"model":[34],"parameters":[35],"known.":[37],"This":[38],"limitation":[39],"addressed":[42],"through":[43],"model-based":[44],"Bayesian":[45,112],"reinforcement":[46],"learning,":[47],"which":[48],"offers":[49],"a":[50,67,115],"rich":[51],"framework":[52],"for":[53,76],"simultaneous":[54],"learning":[55],"and":[56,100],"planning.":[57],"due":[59],"to":[60,71,110],"high":[62],"complexity":[63],"of":[64,91,97],"framework,":[66],"major":[68],"challenge":[69],"is":[70],"scale":[72],"up":[73],"these":[74],"algorithms":[75],"complex":[77],"systems.":[79],"In":[80],"this":[81],"work,":[82],"we":[83,107],"show":[84],"by":[86],"exploiting":[87],"certain":[88],"known":[89],"components":[90],"system,":[93],"such":[94],"as":[95],"knowledge":[96],"symmetrical":[98],"properties,":[99],"an":[102],"approximate":[103],"online":[104],"planning":[105],"algorithm,":[106],"able":[109],"apply":[111],"RL":[113],"realistic":[116],"spoken":[117],"domain.":[120]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}