POMDP-Based Statistical Spoken Dialog Systems: A Review. Young, S., Gašić, M., Thomson, B., & Williams, J. D. 101(5):1160-1179. doi abstract bibtex Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.
@article{youngPOMDPBasedStatisticalSpoken2013,
title = {{{POMDP}}-{{Based Statistical Spoken Dialog Systems}}: {{A Review}}},
volume = {101},
issn = {0018-9219},
doi = {10.1109/JPROC.2012.2225812},
shorttitle = {{{POMDP}}-{{Based Statistical Spoken Dialog Systems}}},
abstract = {Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.},
number = {5},
journaltitle = {Proceedings of the IEEE},
date = {2013-05},
pages = {1160-1179},
keywords = {reinforcement learning,Bayes methods,Belief monitoring,Belief propagation,data-driven framework,exact model representation,explicit Bayesian model,Information processing,Learning systems,Markov processes,Mathematical model,noisy environments,optimisation,optimization,Optimization,partially observable Markov decision process (POMDP),partially observable Markov decision processes,policy optimization,POMDP-based statistical spoken dialog systems,reward-driven process,SDS,Speech processing,speech recognition,Speech recognition,speech recognizers,spoken dialog systems (SDSs),statistical dialog systems},
author = {Young, S. and Gašić, M. and Thomson, B. and Williams, J. D.},
file = {/home/dimitri/Nextcloud/Zotero/storage/8M4JHYJ5/Young et al. - 2013 - POMDP-Based Statistical Spoken Dialog Systems A R.pdf;/home/dimitri/Nextcloud/Zotero/storage/GXZF6FQP/6407655.html}
}
Downloads: 0
{"_id":"CmC4mLphN9Wb8JwAw","bibbaseid":"young-gai-thomson-williams-pomdpbasedstatisticalspokendialogsystemsareview","authorIDs":[],"author_short":["Young, S.","Gašić, M.","Thomson, B.","Williams, J. D."],"bibdata":{"bibtype":"article","type":"article","title":"POMDP-Based Statistical Spoken Dialog Systems: A Review","volume":"101","issn":"0018-9219","doi":"10.1109/JPROC.2012.2225812","shorttitle":"POMDP-Based Statistical Spoken Dialog Systems","abstract":"Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.","number":"5","journaltitle":"Proceedings of the IEEE","date":"2013-05","pages":"1160-1179","keywords":"reinforcement learning,Bayes methods,Belief monitoring,Belief propagation,data-driven framework,exact model representation,explicit Bayesian model,Information processing,Learning systems,Markov processes,Mathematical model,noisy environments,optimisation,optimization,Optimization,partially observable Markov decision process (POMDP),partially observable Markov decision processes,policy optimization,POMDP-based statistical spoken dialog systems,reward-driven process,SDS,Speech processing,speech recognition,Speech recognition,speech recognizers,spoken dialog systems (SDSs),statistical dialog systems","author":[{"propositions":[],"lastnames":["Young"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Gašić"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Thomson"],"firstnames":["B."],"suffixes":[]},{"propositions":[],"lastnames":["Williams"],"firstnames":["J.","D."],"suffixes":[]}],"file":"/home/dimitri/Nextcloud/Zotero/storage/8M4JHYJ5/Young et al. - 2013 - POMDP-Based Statistical Spoken Dialog Systems A R.pdf;/home/dimitri/Nextcloud/Zotero/storage/GXZF6FQP/6407655.html","bibtex":"@article{youngPOMDPBasedStatisticalSpoken2013,\n title = {{{POMDP}}-{{Based Statistical Spoken Dialog Systems}}: {{A Review}}},\n volume = {101},\n issn = {0018-9219},\n doi = {10.1109/JPROC.2012.2225812},\n shorttitle = {{{POMDP}}-{{Based Statistical Spoken Dialog Systems}}},\n abstract = {Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.},\n number = {5},\n journaltitle = {Proceedings of the IEEE},\n date = {2013-05},\n pages = {1160-1179},\n keywords = {reinforcement learning,Bayes methods,Belief monitoring,Belief propagation,data-driven framework,exact model representation,explicit Bayesian model,Information processing,Learning systems,Markov processes,Mathematical model,noisy environments,optimisation,optimization,Optimization,partially observable Markov decision process (POMDP),partially observable Markov decision processes,policy optimization,POMDP-based statistical spoken dialog systems,reward-driven process,SDS,Speech processing,speech recognition,Speech recognition,speech recognizers,spoken dialog systems (SDSs),statistical dialog systems},\n author = {Young, S. and Gašić, M. and Thomson, B. and Williams, J. D.},\n file = {/home/dimitri/Nextcloud/Zotero/storage/8M4JHYJ5/Young et al. - 2013 - POMDP-Based Statistical Spoken Dialog Systems A R.pdf;/home/dimitri/Nextcloud/Zotero/storage/GXZF6FQP/6407655.html}\n}\n\n","author_short":["Young, S.","Gašić, M.","Thomson, B.","Williams, J. D."],"key":"youngPOMDPBasedStatisticalSpoken2013","id":"youngPOMDPBasedStatisticalSpoken2013","bibbaseid":"young-gai-thomson-williams-pomdpbasedstatisticalspokendialogsystemsareview","role":"author","urls":{},"keyword":["reinforcement learning","Bayes methods","Belief monitoring","Belief propagation","data-driven framework","exact model representation","explicit Bayesian model","Information processing","Learning systems","Markov processes","Mathematical model","noisy environments","optimisation","optimization","Optimization","partially observable Markov decision process (POMDP)","partially observable Markov decision processes","policy optimization","POMDP-based statistical spoken dialog systems","reward-driven process","SDS","Speech processing","speech recognition","Speech recognition","speech recognizers","spoken dialog systems (SDSs)","statistical dialog systems"],"downloads":0},"bibtype":"article","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.266Z","downloads":0,"keywords":["reinforcement learning","bayes methods","belief monitoring","belief propagation","data-driven framework","exact model representation","explicit bayesian model","information processing","learning systems","markov processes","mathematical model","noisy environments","optimisation","optimization","optimization","partially observable markov decision process (pomdp)","partially observable markov decision processes","policy optimization","pomdp-based statistical spoken dialog systems","reward-driven process","sds","speech processing","speech recognition","speech recognition","speech recognizers","spoken dialog systems (sdss)","statistical dialog systems"],"search_terms":["pomdp","based","statistical","spoken","dialog","systems","review","young","gašić","thomson","williams"],"title":"POMDP-Based Statistical Spoken Dialog Systems: A Review","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}