{"id":"https://openalex.org/W2083849869","doi":"https://doi.org/10.1109/jstsp.2012.2229962","title":"Building Adaptive Dialogue Systems Via Bayes-Adaptive POMDPs","display_name":"Building Adaptive Dialogue Systems Via Bayes-Adaptive POMDPs","publication_year":2012,"publication_date":"2012-11-27","ids":{"openalex":"https://openalex.org/W2083849869","doi":"https://doi.org/10.1109/jstsp.2012.2229962","mag":"2083849869"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2012.2229962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2012.2229962","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","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/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":true,"raw_author_name":"Shaowei Png","raw_affiliation_strings":["School of Computer Science, McGill University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["Google, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Seattle, WA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002976111","display_name":"Brahim Chaib-draa","orcid":"https://orcid.org/0000-0001-7615-5154"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brahim Chaib-Draa","raw_affiliation_strings":["Computer Science Department, Laval University, Quebec, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Laval University, Quebec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037959209"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":2.9969,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9164708,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":"8","first_page":"917","last_page":"927"},"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":0.9979000091552734,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9722089767456055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7828927636146545},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7623870968818665},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.7340151071548462},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6431305408477783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5994100570678711},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.578400731086731},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5582197308540344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5232385993003845},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48146358132362366},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4404481053352356},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.42247113585472107},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2884600758552551},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.19232740998268127},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15991029143333435}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9722089767456055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828927636146545},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7623870968818665},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.7340151071548462},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6431305408477783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5994100570678711},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.578400731086731},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5582197308540344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5232385993003845},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48146358132362366},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4404481053352356},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.42247113585472107},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2884600758552551},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.19232740998268127},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15991029143333435},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2012.2229962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2012.2229962","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W27627492","https://openalex.org/W34327539","https://openalex.org/W36013382","https://openalex.org/W200223693","https://openalex.org/W1496855202","https://openalex.org/W1580557482","https://openalex.org/W1581952794","https://openalex.org/W1600735390","https://openalex.org/W1681299129","https://openalex.org/W1972247907","https://openalex.org/W2007221309","https://openalex.org/W2011418219","https://openalex.org/W2015936967","https://openalex.org/W2021151961","https://openalex.org/W2034725503","https://openalex.org/W2037897789","https://openalex.org/W2040123554","https://openalex.org/W2049167423","https://openalex.org/W2062244797","https://openalex.org/W2063551842","https://openalex.org/W2083205357","https://openalex.org/W2094134654","https://openalex.org/W2099873296","https://openalex.org/W2107282196","https://openalex.org/W2107886506","https://openalex.org/W2110962519","https://openalex.org/W2112259378","https://openalex.org/W2112476714","https://openalex.org/W2116459397","https://openalex.org/W2117578934","https://openalex.org/W2132997613","https://openalex.org/W2133434946","https://openalex.org/W2144794447","https://openalex.org/W2144913588","https://openalex.org/W2147933644","https://openalex.org/W2153385324","https://openalex.org/W2158907787","https://openalex.org/W2160219061","https://openalex.org/W2160422981","https://openalex.org/W2168359464","https://openalex.org/W2168839459","https://openalex.org/W2171084228","https://openalex.org/W2184461682","https://openalex.org/W2202767678","https://openalex.org/W2438667436","https://openalex.org/W2569188995","https://openalex.org/W2791590751","https://openalex.org/W3004707083","https://openalex.org/W3016548437","https://openalex.org/W3099293669","https://openalex.org/W3101822862","https://openalex.org/W3150017941","https://openalex.org/W6601091514","https://openalex.org/W6601465738","https://openalex.org/W6629614444","https://openalex.org/W6634664345","https://openalex.org/W6674711614","https://openalex.org/W6675993619","https://openalex.org/W6676742712","https://openalex.org/W6681472862","https://openalex.org/W6684973485","https://openalex.org/W6684985892"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W131709709"],"abstract_inverted_index":{"Recent":[0],"research":[1,22],"has":[2],"shown":[3],"that":[4],"effective":[5],"dialogue":[6,25,91],"management":[7],"can":[8,72],"be":[9,73],"achieved":[10],"through":[11],"the":[12,29,32,55],"Partially":[13],"Observable":[14],"Markov":[15],"Decision":[16],"Process":[17],"(POMDP)":[18],"framework.":[19],"However":[20],"past":[21],"on":[23],"POMDP-based":[24],"systems":[26],"usually":[27],"assumed":[28],"parameters":[30,57],"of":[31,42],"decision":[33],"process":[34],"were":[35],"known":[36],"a":[37,48,62],"priori.":[38],"The":[39],"main":[40],"contribution":[41],"this":[43],"paper":[44],"is":[45],"to":[46,75,83],"present":[47],"Bayesian":[49],"reinforcement":[50],"learning":[51,54,84],"framework":[52],"for":[53,87],"POMDP":[56],"online":[58],"from":[59],"data,":[60],"in":[61],"decision-theoretic":[63],"manner.":[64],"We":[65],"discuss":[66],"various":[67],"approximations":[68],"and":[69,79],"assumptions":[70],"which":[71],"leveraged":[74],"ensure":[76],"computational":[77],"tractability,":[78],"apply":[80],"these":[81],"techniques":[82],"observation":[85],"models":[86],"several":[88],"simulated":[89],"spoken":[90],"domains.":[92]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}