{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T01:15:03Z","timestamp":1787706903958,"version":"build-2784847793"},"reference-count":155,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2013,5,1]],"date-time":"2013-05-01T00:00:00Z","timestamp":1367366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/jproc.2012.2225812","type":"journal-article","created":{"date-parts":[[2013,1,9]],"date-time":"2013-01-09T17:35:51Z","timestamp":1357752951000},"page":"1160-1179","source":"Crossref","is-referenced-by-count":399,"title":["POMDP-Based Statistical Spoken Dialog Systems: A Review"],"prefix":"10.1109","volume":"101","author":[{"given":"Steve","family":"Young","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milica","family":"Gasic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Blaise","family":"Thomson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason D.","family":"Williams","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"119","article-title":"State abstraction for programmable reinforcement learning agents","author":"andre","year":"2002","journal-title":"Proc 18th Nat Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902050"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430163"},{"key":"ref32","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075127"},{"key":"ref30","first-page":"13","article-title":"A &#x2018;K hypotheses + other&#x2019; belief updating model","author":"bohus","year":"2006","journal-title":"Proc AAAI Workshop Statist Empirical Approaches Spoken Dialogue Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566498"},{"key":"ref36","first-page":"493","article-title":"The permutable POMDP: Fast solutions to POMDPs for preference elicitation","author":"doshi","year":"2008","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref35","first-page":"1029","article-title":"Lossless value directed compression of complex user goal states for statistical spoken dialogue systems","author":"crook","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700896"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.07.003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518765"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557710"},{"key":"ref20","first-page":"1243","article-title":"Point-based policy iteration","author":"ji","year":"2007","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324908005032"},{"key":"ref21","first-page":"76","article-title":"Factored partially observable Markov decision processes for dialogue management","author":"williams","year":"2005","journal-title":"Proc Workshop Knowl Reasoning Practical Dialog Syst IJCAI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1622064.1622088"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367185"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566539"},{"key":"ref26","article-title":"Effective handling of dialogue state in the hidden information state POMDP dialogue manager","volume":"7","author":"gai","year":"2011","journal-title":"ACM Trans Speech Lang Process"},{"key":"ref100","first-page":"1153","article-title":"Evaluating semantic-level confidence scores with multiple hypotheses","author":"thomson","year":"2008","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494939"},{"key":"ref50","first-page":"185","article-title":"Learning more effective dialogue strategies using limited dialogue move features","author":"frampton","year":"2006","journal-title":"Proc Annu Meeting Assoc Comput Linguist"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.07-028-R2-05-82"},{"key":"ref154","first-page":"201","article-title":"A Computational architecture for conversation","author":"horvitz","year":"1999","journal-title":"Proc 7th Int Conf User Model"},{"key":"ref153","first-page":"230","article-title":"Inferring informational goals from free-text queries: A Bayesian approach","author":"heckerman","year":"1998","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.814380"},{"key":"ref150","first-page":"268","article-title":"Combining reinforcement learning with information-state update rules","author":"heeman","year":"2007","journal-title":"Proc Conf Human Lang Technol North Amer Chapter Assoc Comput Linguist"},{"key":"ref152","article-title":"Conversational games, belief revision and Bayesian networks","author":"pulman","year":"1996","journal-title":"Proc CLIN VII 7th Comput Linguist Meeting"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367189"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30211-7_1"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521447"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220870"},{"key":"ref149","article-title":"Using reinforcement learning to build a better model of dialogue state","author":"tetreault","year":"2006","journal-title":"Proc of the Association for Computational Linguistics"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21043-3_11"},{"key":"ref58","article-title":"Unsupervised clustering of probability distributions of semantic frame graphs for pomdp-based spoken dialogue systems with summary space","author":"pinault","year":"2011","journal-title":"Proc Workshop Knowl Reasoning Practical Dialog Syst IJCAI"},{"key":"ref57","first-page":"1321","article-title":"Semantic graph clustering for POMDP-based spoken dialog systems","author":"pinault","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref56","article-title":"Learning the reward model of dialogue POMDPs from data","author":"boularias","year":"2010","journal-title":"Proc NIPS Workshop of Mach Learn for Assistive Tech"},{"key":"ref55","first-page":"284","article-title":"Feature-based summary space for stochastic dialogue modeling with hierarchical semantic frames","author":"pinault","year":"2009","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref54","first-page":"215","article-title":"Practical dialogue manager development using POMDPs","author":"bui","year":"2007","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref53","first-page":"34","article-title":"A tractable DDN-POMDP approach to affective dialogue modeling for general probabilistic frame-based dialogue systems","author":"bui","year":"2007","journal-title":"Proc Workshop Knowl Reasoning Practical Dialog Syst IJCAI"},{"key":"ref52","article-title":"SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces","author":"kurniawati","year":"2008","journal-title":"Proc Robot Sci Syst"},{"key":"ref40","first-page":"1173","article-title":"The best of both worlds: Unifying conventional dialog systems and POMDPs","author":"williams","year":"2008","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.935874"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/5.880078"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.03.010"},{"key":"ref5","author":"oshry","year":"2009","journal-title":"Voice extensible markup language (VoiceXML) 3 0"},{"key":"ref8","first-page":"2","article-title":"Spoken dialog challenge 2010: Comparison of live and control test results","author":"black","year":"2011","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref49","first-page":"68","article-title":"Hybrid reinforcement\/supervised learning for dialogue policies from communicator data","author":"henderson","year":"2005","journal-title":"Proc Workshop Knowl Reasoning Practical Dialog Syst IJCAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(97)00021-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075231"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326775"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1289189.1289246"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.855836"},{"key":"ref47","first-page":"547","article-title":"Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces","author":"cuayhuitl","year":"2006","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.04.001"},{"key":"ref41","first-page":"7","article-title":"Towards relational POMDPs for adaptive dialogue management","author":"lison","year":"2010","journal-title":"Proc Annu Meeting Assoc Comput Linguist"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1966407.1966412"},{"key":"ref43","first-page":"2475","article-title":"Reinforcement learning for dialog management using least-squares policy iteration and fast feature selection","author":"li","year":"2009","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3115\/1622064.1622098"},{"key":"ref126","first-page":"409","author":"hirschman","year":"1997","journal-title":"Overview of Evaluation in Speech and Natural Language Processing"},{"key":"ref125","first-page":"130","article-title":"An empirical evaluation of a statistical dialog system in public use","author":"williams","year":"2011","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.3115\/1556328.1556329"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000944"},{"key":"ref72","first-page":"84","article-title":"Reinforcement learning of question-answering dialogue policies for virtual museum guides","author":"misu","year":"2012","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.658989"},{"key":"ref71","first-page":"221","article-title":"Modeling spoken decision making dialogue and optimization of its dialogue strategy","author":"misu","year":"2011","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979652"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1966407.1966411"},{"key":"ref76","first-page":"45","article-title":"quantitative evaluation of user simulation techniques for spoken dialogue systems","author":"schatzmann","year":"2005","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref130","article-title":"Reinforcement learning for spoken dialogue systems","author":"singh","year":"1999","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.05.007"},{"key":"ref74","author":"hastie","year":"2012","journal-title":"Data-Driven Methods for Adaptive Spoken Dialogue Systems Computational Learning for Conversational Interfaces"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000343"},{"key":"ref133","author":"schatzmann","year":"2008","journal-title":"Statistical User and Error Modelling for Spoken Dialogue Systems"},{"key":"ref134","first-page":"456","article-title":"Back-off action selection in summary space-based POMDP dialogue systems","author":"gai","year":"2009","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref131","first-page":"1025","article-title":"Evaluating dialogue strategies under communication errors using computer-to-computer simulation","volume":"e81 d","author":"watambe","year":"1998","journal-title":"IEICE Trans Inf Syst"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.658991"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.3115\/1622064.1622097"},{"key":"ref79","first-page":"893","article-title":"Learning user simulations for information state update dialogue systems","author":"georgila","year":"2005","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref136","first-page":"1576","article-title":"Collecting voices from the cloud","author":"mcgraw","year":"2010","journal-title":"Proc Int Conf Lang Resources Eval"},{"key":"ref135","first-page":"3061","article-title":"Real user evaluation of spoken dialogue systems using amazon mechanical turk","author":"jurek","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref138","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.21437\/Eurospeech.1997-380","article-title":"A stochastic model of computer-human interaction for learning dialogue strategies","author":"levin","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref137","doi-asserted-by":"crossref","first-page":"2169","DOI":"10.21437\/Eurospeech.2001-511","article-title":"Spoken dialogue management as planning and acting under uncertainty","author":"zhang","year":"2001","journal-title":"Proc EUROSPEECH"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30353-1_24"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674402"},{"key":"ref62","article-title":"Integrating expert knowledge into POMDP optimization for spoken dialog systems","author":"williams","year":"2008","journal-title":"Proc AAAI Workshop Adv POMDP Solvers"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947627"},{"key":"ref63","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref64","article-title":"<ref_formula><tex Notation=\"TeX\">$k$<\/tex><\/ref_formula>-nearest neighbor Monte-Carlo control algorithm for POMDP-based dialogue systems","author":"lefevre","year":"2009","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.3115\/980691.980788"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"ref141","first-page":"309","article-title":"Automatic detection of poor speech recognition at the dialogue level","author":"kearns","year":"1999","journal-title":"Proc Annu Meeting Assoc Comput Linguist"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref142","first-page":"1233","article-title":"Fast reinforcement learning of dialog strategies","author":"goddeau","year":"2000","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2000.0593"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref144","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1613\/jair.859","article-title":"Optimizing dialogue management with reinforcement learning: Experiments with the NJFun system","volume":"16","author":"singh","year":"2002","journal-title":"J Artif Intell Res"},{"key":"ref2","author":"smith","year":"1994","journal-title":"Spoken Natural Language Dialog Systems A Practical Approach"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700878"},{"key":"ref145","first-page":"325","article-title":"Learning dialogue policies using state aggregation in reinforcement learning","author":"denecke","year":"2004","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref1","author":"de mori","year":"1998","journal-title":"Spoken Dialogues with Computers"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700863"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005671"},{"key":"ref108","first-page":"362","article-title":"Expectation propagation for approximate Bayesian inference","author":"minka","year":"2001","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref94","first-page":"1025","article-title":"User simulation in dialogue systems using inverse reinforcement learning","author":"chandramohan","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557722"},{"key":"ref93","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1080\/09540090802413145"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.03.002"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777855"},{"key":"ref91","first-page":"598","article-title":"Training a BN-based user model for dialogue simulation with missing data","author":"rossignol","year":"2011","journal-title":"Proc Int Joint Conf Natural Lang Process"},{"key":"ref104","first-page":"191","article-title":"Exploiting the ASR N-best by tracking multiple dialog state hypotheses","author":"williams","year":"2008","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.855836"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2076394"},{"key":"ref102","first-page":"1","article-title":"Comparing user simulation models for dialog strategy learning","author":"hua ai","year":"2007","journal-title":"Proc Conf North Amer Chapt Assoc Comput Linguist"},{"key":"ref111","first-page":"90","article-title":"Natural belief-critic: A reinforcement algorithm for parameter estimation in statistical spoken dialogue systems","author":"jurek","year":"2010","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref112","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref110","author":"thomson","year":"2009","journal-title":"Statistical Methods for Spoken Dialogue Management"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430167"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74628-7_74"},{"key":"ref96","first-page":"861","article-title":"Comparing ASR modeling methods for spoken dialogue simulation and optimal strategy learning","author":"pietquin","year":"2005","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659954"},{"key":"ref10","first-page":"9","article-title":"Talking to machines (statistically speaking)","author":"young","year":"2002","journal-title":"Proc Int l Conf Spoken Language Processing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref13","first-page":"211","article-title":"Solving POMDPs by searching in policy space","author":"hansen","year":"1998","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref14","first-page":"1555","author":"littman","year":"2002","journal-title":"Advances in Neural Information Processing Systems 14"},{"key":"ref15","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927543"},{"key":"ref16","first-page":"1025","article-title":"Point-based value iteration: An anytime algorithm for POMDPs","author":"pineau","year":"2003","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref82","article-title":"Cluster-based user simulations for learning dialogue strategies","author":"rieser","year":"2006","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref117","first-page":"312","article-title":"On-line policy optimisation of spoken dialogue systems via live interaction with human subjects","author":"gai","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref17","first-page":"520","article-title":"Heuristic search value iteration for POMDPs","author":"smith","year":"2004","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859185"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1613\/jair.1659","article-title":"Perseus: Randomized point-based value iteration for POMDPs","volume":"24","author":"spaan","year":"2005","journal-title":"J Artif Intell Res"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614146"},{"key":"ref119","first-page":"157","article-title":"Managing uncertainty within the KTD framework","author":"geist","year":"2011","journal-title":"Proc Workshop Active Learn Exp Design"},{"key":"ref19","first-page":"542","article-title":"Point-based POMDP algorithms: Improved analysis and implementation","author":"smith","year":"2005","journal-title":"Proc 13th Annu Conf Uncertainty Artif Intell"},{"key":"ref83","first-page":"425","article-title":"Consistent goal-directed user model for realistic man-machine task-oriented spoken dialogue simulation","author":"pietquin","year":"2006","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref114","author":"gai","year":"2011","journal-title":"Statistical Dialogue Modelling"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"ref116","first-page":"201","article-title":"Gaussian processes for fast policy optimisation of a POMDP dialogue manager for a real-world task","author":"gai","year":"2010","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref80","first-page":"45","article-title":"User simulation for spoken dialogue systems: Learning and evaluation","author":"georgila","year":"2006","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref115","author":"engel","year":"2005","journal-title":"Algorithms and Representations for Reinforcement Learning"},{"key":"ref120","first-page":"1878","article-title":"Sample efficient on-line learning of optimal dialogue policies with Kalman temporal differences","author":"pietquin","year":"2011","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566485"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.3115\/1564144.1564145"},{"key":"ref122","first-page":"142","article-title":"&#x2018;The day after the day after tomorrow?&#x2019; A machine learning approach to adaptive temporal expression generation: Training and evaluation with real users","author":"janarthanam","year":"2011","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref123","article-title":"Multimodal dialog system using hidden information state dialog manager","author":"kim","year":"2007","journal-title":"Proc Int Conf Multimodal Interfaces Demonstration Session"},{"key":"ref85","first-page":"2697","article-title":"Knowledge consistent user simulations for dialog systems","author":"ai","year":"2007","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2012071"},{"key":"ref87","first-page":"116","article-title":"Parameter estimation for agenda-based user simulation","author":"keizer","year":"2010","journal-title":"12th Annual Meeting of the Special Interest Group on Discourse and Dialogue"},{"key":"ref88","author":"pietquin","year":"2004","journal-title":"A Framework for Unsupervised Learning of Dialogue Strategies"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5\/6504474\/06407655.pdf?arnumber=6407655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T10:45:14Z","timestamp":1714819514000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6407655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":155,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2012.2225812","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,5]]}}}