{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T04:40:10Z","timestamp":1751776810141,"version":"3.41.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319921075"},{"type":"electronic","value":"9783319921082"}],"license":[{"start":{"date-parts":[[2018,8,2]],"date-time":"2018-08-02T00:00:00Z","timestamp":1533168000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-319-92108-2_22","type":"book-chapter","created":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T10:54:51Z","timestamp":1533120891000},"page":"211-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Applicability of a User Satisfaction-Based Reward for Dialogue Policy Learning"],"prefix":"10.1007","author":[{"given":"Stefan","family":"Ultes","sequence":"first","affiliation":[]},{"given":"Juliana","family":"Miehle","sequence":"additional","affiliation":[]},{"given":"Wolfgang","family":"Minker","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,2]]},"reference":[{"key":"22_CR1","unstructured":"El\u00a0Asri L, Khouzaimi H, Laroche R, Pietquin O (2014) Ordinal regression for interaction quality prediction. In: Proceedings of ICASSP. IEEE, pp 3245\u20133249"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"El Asri L, Laroche R, Pietquin O (2012) Reward function learning for dialogue management. In: Proceedings of the 6th STAIRS. IOS Press, pp 95\u2013106","DOI":"10.3233\/978-1-61499-096-3-95"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"El\u00a0Asri L, Laroche R, Pietquin O (2013) Reward shaping for statistical optimisation of dialogue management. In: Statistical language and speech processing. Springer, pp 93\u2013101","DOI":"10.1007\/978-3-642-39593-2_8"},{"key":"22_CR4","unstructured":"Ga\u0161i\u0107 M, Breslin C, Henderson M, Kim D, Szummer M, Thomson B, Tsiakoulis P, Young SJ (2013) On-line policy optimisation of Bayesian spoken dialogue systems via human interaction. In: Proceedings of ICASSP. IEEE, pp 8367\u20138371"},{"key":"22_CR5","unstructured":"Lee S, Eskenazi M (2012) An unsupervised approach to user simulation: toward self-improving dialog systems. In: Proceedings of 13th SIGDial. ACL, pp 50\u201359"},{"key":"22_CR6","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.21437\/Eurospeech.1997-380","volume":"97","author":"E Levin","year":"1997","unstructured":"Levin E, Pieraccini R (1997) A stochastic model of computer-human interaction for learning dialogue strategies. Eurospeech 97:1883\u20131886","journal-title":"Eurospeech"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Raux A, Bohus D, Langner B, Black AW, Eskenazi M (2006) Doing research on a deployed spoken dialogue system: one year of let\u2019s go! experience. In: Proceedings of ICSLP","DOI":"10.21437\/Interspeech.2006-17"},{"key":"22_CR8","unstructured":"Rieser V, Lemon O (2008) Learning effective multimodal dialogue strategies from wizard-of-oz data: bootstrapping and evaluation. In: Proceedings of 46th ACL-HLT. ACL, pp 638\u2013646"},{"key":"22_CR9","unstructured":"Schmitt A, Schatz B, Minker W (2011) Modeling and predicting quality in spoken human-computer interaction. In: Proceedings of 12th SIGDial. ACL, Portland, OR, pp 173\u2013184"},{"key":"22_CR10","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2015.06.003","volume":"74","author":"A Schmitt","year":"2015","unstructured":"Schmitt A, Ultes S (2015) Interaction quality: assessing the quality of ongoing spoken dialog interaction by experts\u2013and how it relates to user satisfaction. Speech Commun 74:12\u201336. https:\/\/doi.org\/10.1016\/j.specom.2015.06.003","journal-title":"Speech Commun"},{"key":"22_CR11","unstructured":"Schmitt A, Ultes S, Minker W (2012) A parameterized and annotated spoken dialog corpus of the cmu let\u2019s go bus information system. In: Proceedings of LREC, pp 3369\u2013337"},{"key":"22_CR12","unstructured":"Su PH, Ga\u0161i\u0107 M, Mrk\u0161i\u0107 N, Rojas-Barahona L, Ultes S, Vandyke D, Wen TH, Young S (2016) On-line active reward learning for policy optimisation in spoken dialogue systems. In: Proceedings of 54th ACL. ACL, pp 2431\u20132441"},{"key":"22_CR13","doi-asserted-by":"publisher","unstructured":"Ultes S, Budzianowski P, Casanueva I, Mrk\u0161i\u0107 N, Rojas-Barahona L, Su PH, Wen TH, Ga\u0161i\u0107 M, Young S (2017) Domain-independent user satisfaction reward estimation for dialogue policy learning. In: Proceedings of Interspeech. ISCA, pp 1721\u20131725. https:\/\/doi.org\/10.21437\/Interspeech.2017-1032","DOI":"10.21437\/Interspeech.2017-1032"},{"key":"22_CR14","doi-asserted-by":"publisher","unstructured":"Ultes S, Dikme H, Minker W (2016) Dialogue management for user-centered adaptive dialogue. In: Situated dialog in speech-based human-computer interaction. Springer International Publishing, Cham, pp 51\u201361. https:\/\/doi.org\/10.1007\/978-3-319-21834-2_5","DOI":"10.1007\/978-3-319-21834-2_5"},{"key":"22_CR15","doi-asserted-by":"publisher","unstructured":"Ultes S, Heinroth T, Schmitt A, Minker W (2011) A theoretical framework for a user-centered spoken dialog manager. In: Proceedings of the paralinguistic information and its integration in spoken dialogue systems workshop. Springer New York, pp 241\u2013246. https:\/\/doi.org\/10.1007\/978-1-4614-1335-6_24","DOI":"10.1007\/978-1-4614-1335-6_24"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Ultes S, Kraus M, Schmitt A, Minker W (2015) Quality-adaptive spoken dialogue initiative selection and implications on reward modelling. In: Proceedings of 16th SIGDIAL. ACL, pp 374\u2013383","DOI":"10.18653\/v1\/W15-4649"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Ultes S, Minker W (2014) Interaction quality estimation in spoken dialogue systems using hybrid-HMMs. In: Proceedings of 15th SIGDIAL. ACL, pp 208\u2013217","DOI":"10.3115\/v1\/W14-4328"},{"issue":"5","key":"22_CR18","doi-asserted-by":"publisher","first-page":"523","DOI":"10.3233\/ais-140275","volume":"6","author":"S Ultes","year":"2014","unstructured":"Ultes S, Minker W (2014) Managing adaptive spoken dialogue for intelligent environments. J Ambient Intell Smart Environ 6(5):523\u2013539. https:\/\/doi.org\/10.3233\/ais-140275","journal-title":"J Ambient Intell Smart Environ"},{"key":"22_CR19","unstructured":"Ultes S, Schmitt A, Minker W (2012) Towards quality-adaptive spoken dialogue management. In: NAACL-HLT workshop on future directions and needs in the spoken dialog community: tools and data (SDCTD 2012). ACL, Montr\u00e9al, Canada, pp 49\u201352"},{"key":"22_CR20","unstructured":"Ultes S, Schmitt A, Minker W (2013) On quality ratings for spoken dialogue systems\u2014experts versus users. In: Proceedings of the 2013 NAACL-HLT. ACL, pp 569\u2013578"},{"key":"22_CR21","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1613\/jair.713","volume":"12","author":"M Walker","year":"2000","unstructured":"Walker M (2000) An application of reinforcement learning to dialogue strategy selection in a spoken dialogue system for email. J Artif Intell Res 12:387\u2013416","journal-title":"J Artif Intell Res"},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Walker M, Litman DJ, Kamm CA, Abella A (1997) PARADISE: a framework for evaluating spoken dialogue agents. In: Proceedings of 8th EACL. ACL, Morristown, NJ, USA, pp 271\u2013280. https:\/\/doi.org\/10.3115\/979617.979652","DOI":"10.3115\/979617.979652"},{"key":"22_CR23","unstructured":"Williams JD, Young SJ (2004) Characterizing task-oriented dialog using a simulated asr chanel. In: Proceedings of 8th Interspeech, pp 185\u2013188"},{"issue":"5","key":"22_CR24","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/JPROC.2012.2225812","volume":"101","author":"SJ Young","year":"2013","unstructured":"Young SJ, Ga\u0161i\u0107 M, Thomson B, Williams JD (2013) POMDP-based statistical spoken dialog systems: a review. Proc IEEE 101(5):1160\u20131179","journal-title":"Proc IEEE"}],"container-title":["Lecture Notes in Electrical Engineering","Advanced Social Interaction with Agents"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92108-2_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T04:27:44Z","timestamp":1751776064000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92108-2_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,2]]},"ISBN":["9783319921075","9783319921082"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92108-2_22","relation":{},"ISSN":["1876-1100","1876-1119"],"issn-type":[{"type":"print","value":"1876-1100"},{"type":"electronic","value":"1876-1119"}],"subject":[],"published":{"date-parts":[[2018,8,2]]},"assertion":[{"value":"2 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}