{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:27:33Z","timestamp":1750220853893,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T00:00:00Z","timestamp":1571011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,14]]},"DOI":"10.1145\/3350546.3352501","type":"proceedings-article","created":{"date-parts":[[2019,10,18]],"date-time":"2019-10-18T12:57:15Z","timestamp":1571403435000},"page":"59-67","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Reinforcement Learning for Personalized Dialogue Management"],"prefix":"10.1145","author":[{"given":"Floris","family":"den Hengst","sequence":"first","affiliation":[{"name":"ING Group N.V., Netherlands"}]},{"given":"Mark","family":"Hoogendoorn","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Netherlands"}]},{"given":"Frank","family":"van Harmelen","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Netherlands"}]},{"given":"Joost","family":"Bosman","sequence":"additional","affiliation":[{"name":"ING Group N.V., Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2019,10,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Springer","author":"Adomavicius Gediminas","year":"2011","unstructured":"[ 1 ] Gediminas Adomavicius and Alexander Tuzhilin . Context-aware recommender systems. In Recommender systems handbook, pages 217\u2013253 . Springer , 2011 . [1] Gediminas Adomavicius and Alexander Tuzhilin. Context-aware recommender systems. In Recommender systems handbook, pages 217\u2013253. Springer, 2011."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/975284"},{"key":"e_1_3_2_1_3_1","first-page":"243","volume-title":"2015 International Conference on Big Data and Smart Computing (BigComp)","author":"Bang Jeesoo","unstructured":"[ 3 ] Jeesoo Bang , Hyungjong Noh , Yonghee Kim , and Gary\u00a0Geunbae Lee . Example-based chat-oriented dialogue system with personalized long-term memory . In 2015 International Conference on Big Data and Smart Computing (BigComp) , pages 238\u2013 243 . IEEE, 2015. [3] Jeesoo Bang, Hyungjong Noh, Yonghee Kim, and Gary\u00a0Geunbae Lee. Example-based chat-oriented dialogue system with personalized long-term memory. In 2015 International Conference on Big Data and Smart Computing (BigComp), pages 238\u2013243. IEEE, 2015."},{"key":"e_1_3_2_1_4_1","volume-title":"Language files: Materials for an introduction to language and linguistics","author":"Bergmann Anouschka","year":"2007","unstructured":"[ 4 ] Anouschka Bergmann , Kathleen\u00a0Currie Hall , and Sharon\u00a0Miriam Ross . Language files: Materials for an introduction to language and linguistics . Ohio State University Press , 2007 . [4] Anouschka Bergmann, Kathleen\u00a0Currie Hall, and Sharon\u00a0Miriam Ross. Language files: Materials for an introduction to language and linguistics. Ohio State University Press, 2007."},{"key":"e_1_3_2_1_5_1","volume-title":"Deep Reinforcement Learning Symposium, 31st Conference on Neural Information Processing Systems","author":"Casanueva I\u00f1igo","year":"2017","unstructured":"[ 5 ] I\u00f1igo Casanueva , Pawe\u0142 Budzianowski , Pei-Hao Su , Nikola Mrk\u0161i\u0107 , Tsung-Hsien Wen , Stefan Ultes , Lina Rojas-Barahona , Steve Young , and Milica Ga\u0161i\u0107 . A benchmarking environment for reinforcement learning based task oriented dialogue management . In Deep Reinforcement Learning Symposium, 31st Conference on Neural Information Processing Systems , 2017 . [5] I\u00f1igo Casanueva, Pawe\u0142 Budzianowski, Pei-Hao Su, Nikola Mrk\u0161i\u0107, Tsung-Hsien Wen, Stefan Ultes, Lina Rojas-Barahona, Steve Young, and Milica Ga\u0161i\u0107. A benchmarking environment for reinforcement learning based task oriented dialogue management. In Deep Reinforcement Learning Symposium, 31st Conference on Neural Information Processing Systems, 2017."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4603"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3613"},{"key":"e_1_3_2_1_8_1","first-page":"204","volume-title":"Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue","author":"Ga\u0161i\u0107 Milica","unstructured":"[ 8 ] Milica Ga\u0161i\u0107 , Filip Jur\u010d\u00ed\u010dek , Simon Keizer , Fran\u00e7ois Mairesse , Blaise Thomson , Kai Yu , and Steve Young . Gaussian processes for fast policy optimisation of POMDP-based dialogue managers . In Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue , pages 201\u2013 204 . Association for Computational Linguistics, 2010. [8] Milica Ga\u0161i\u0107, Filip Jur\u010d\u00ed\u010dek, Simon Keizer, Fran\u00e7ois Mairesse, Blaise Thomson, Kai Yu, and Steve Young. Gaussian processes for fast policy optimisation of POMDP-based dialogue managers. In Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 201\u2013204. Association for Computational Linguistics, 2010."},{"key":"e_1_3_2_1_9_1","first-page":"983","volume-title":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems","author":"Genevay Aude","year":"2016","unstructured":"[ 9 ] Aude Genevay and Romain Laroche . Transfer learning for user adaptation in spoken dialogue systems . In Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems , pages 975\u2013 983 , 2016 . [9] Aude Genevay and Romain Laroche. Transfer learning for user adaptation in spoken dialogue systems. In Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, pages 975\u2013983, 2016."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44527-7_10"},{"key":"e_1_3_2_1_11_1","first-page":"1865","volume-title":"International Conference on Machine Learning","author":"Haarnoja Tuomas","year":"2018","unstructured":"[ 11 ] Tuomas Haarnoja , Aurick Zhou , Pieter Abbeel , and Sergey Levine . Soft actor-critic : Off-policy maximum entropy deep reinforcement learning with a stochastic actor . In International Conference on Machine Learning , pages 1856\u2013 1865 , 2018 . [11] Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International Conference on Machine Learning, pages 1856\u20131865, 2018."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4337"},{"key":"e_1_3_2_1_13_1","first-page":"86","volume-title":"Proceedings of the fourth ACM conference on Recommender systems","author":"Karatzoglou Alexandros","unstructured":"[ 13 ] Alexandros Karatzoglou , Xavier Amatriain , Linas Baltrunas , and Nuria Oliver . Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering . In Proceedings of the fourth ACM conference on Recommender systems , pages 79\u2013 86 . ACM, 2010. [13] Alexandros Karatzoglou, Xavier Amatriain, Linas Baltrunas, and Nuria Oliver. Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. In Proceedings of the fourth ACM conference on Recommender systems, pages 79\u201386. ACM, 2010."},{"key":"e_1_3_2_1_14_1","first-page":"87","volume-title":"International Workshop on Multimodal Analyses Enabling Artificial Agents in Human-Machine Interaction","author":"Kim Yonghee","unstructured":"[ 14 ] Yonghee Kim , Jeesoo Bang , Junhwi Choi , Seonghan Ryu , Sangjun Koo , and Gary\u00a0Geunbae Lee . Acquisition and use of long-term memory for personalized dialog systems . In International Workshop on Multimodal Analyses Enabling Artificial Agents in Human-Machine Interaction , pages 78\u2013 87 . Springer, 2014. [14] Yonghee Kim, Jeesoo Bang, Junhwi Choi, Seonghan Ryu, Sangjun Koo, and Gary\u00a0Geunbae Lee. Acquisition and use of long-term memory for personalized dialog systems. In International Workshop on Multimodal Analyses Enabling Artificial Agents in Human-Machine Interaction, pages 78\u201387. Springer, 2014."},{"key":"e_1_3_2_1_15_1","first-page":"670","volume-title":"Proceedings of the 19th international conference on World wide web","author":"Li Lihong","unstructured":"[ 15 ] Lihong Li , Wei Chu , John Langford , and Robert\u00a0 E Schapire . A contextual-bandit approach to personalized news article recommendation . In Proceedings of the 19th international conference on World wide web , pages 661\u2013 670 . ACM, 2010. [15] Lihong Li, Wei Chu, John Langford, and Robert\u00a0E Schapire. A contextual-bandit approach to personalized news article recommendation. In Proceedings of the 19th international conference on World wide web, pages 661\u2013670. ACM, 2010."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/990820.990893"},{"key":"e_1_3_2_1_17_1","first-page":"89","volume-title":"Proceedings of the 1st international workshop on Utility-based data mining","author":"Madani Omid","unstructured":"[ 17 ] Omid Madani and Dennis DeCoste . Contextual recommender problems . In Proceedings of the 1st international workshop on Utility-based data mining , pages 86\u2013 89 . ACM, 2005. [17] Omid Madani and Dennis DeCoste. Contextual recommender problems. In Proceedings of the 1st international workshop on Utility-based data mining, pages 86\u201389. ACM, 2005."},{"key":"e_1_3_2_1_18_1","volume-title":"Dynamic personalization in conversational recommender systems. Information Systems and e-Business Management, 12(2):213\u2013238","author":"Mahmood Tariq","year":"2014","unstructured":"[ 18 ] Tariq Mahmood , Ghulam Mujtaba , and Adriano Venturini . Dynamic personalization in conversational recommender systems. Information Systems and e-Business Management, 12(2):213\u2013238 , 2014 . [18] Tariq Mahmood, Ghulam Mujtaba, and Adriano Venturini. Dynamic personalization in conversational recommender systems. Information Systems and e-Business Management, 12(2):213\u2013238, 2014."},{"issue":"4","key":"e_1_3_2_1_19_1","first-page":"12","article-title":"A proposal for the Dartmouth summer research project on artificial intelligence, august 31, 1955","volume":"27","author":"McCarthy John","year":"2006","unstructured":"[ 19 ] John McCarthy , Marvin\u00a0 L Minsky , Nathaniel Rochester , and Claude\u00a0 E Shannon . A proposal for the Dartmouth summer research project on artificial intelligence, august 31, 1955 . AI magazine , 27 ( 4 ): 12 , 2006 . [19] John McCarthy, Marvin\u00a0L Minsky, Nathaniel Rochester, and Claude\u00a0E Shannon. A proposal for the Dartmouth summer research project on artificial intelligence, august 31, 1955. AI magazine, 27(4):12, 2006.","journal-title":"AI magazine"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11938"},{"key":"e_1_3_2_1_22_1","volume-title":"Springer","author":"Pazzani J","year":"2007","unstructured":"[ 22 ] Michael\u00a0 J Pazzani and Daniel Billsus . Content-based recommendation systems. In The adaptive web, pages 325\u2013341 . Springer , 2007 . [22] Michael\u00a0J Pazzani and Daniel Billsus. Content-based recommendation systems. In The adaptive web, pages 325\u2013341. Springer, 2007."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3975(01)00303-6"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075231"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614146"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700826"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5518"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622467.1622479"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/mind\/LIX.236.433"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_32_1","first-page":"413","volume-title":"Proceedings of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Williams Jason","year":"2013","unstructured":"[ 32 ] Jason Williams , Antoine Raux , Deepak Ramachandran , and Alan Black . The dialog state tracking challenge . In Proceedings of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL) , pages 404\u2013 413 , 2013 . [32] Jason Williams, Antoine Raux, Deepak Ramachandran, and Alan Black. The dialog state tracking challenge. In Proceedings of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 404\u2013413, 2013."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.008"},{"key":"e_1_3_2_1_34_1","volume-title":"Sixteenth Annual Conference of the International Speech Communication Association","author":"Li Miao","year":"2015","unstructured":"[ 34 ] Ji\u00a0Wu, Miao Li , and Chin-Hui Lee . An entropy minimization framework for goal-driven dialogue management . In Sixteenth Annual Conference of the International Speech Communication Association , 2015 . [34] Ji\u00a0Wu, Miao Li, and Chin-Hui Lee. An entropy minimization framework for goal-driven dialogue management. In Sixteenth Annual Conference of the International Speech Communication Association, 2015."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"}],"event":{"name":"WI '19: IEEE\/WIC\/ACM International Conference on Web Intelligence","acronym":"WI '19","location":"Thessaloniki Greece"},"container-title":["IEEE\/WIC\/ACM International Conference on Web Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3350546.3352501","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3350546.3352501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:20Z","timestamp":1750202600000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3350546.3352501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,14]]},"references-count":34,"alternative-id":["10.1145\/3350546.3352501","10.1145\/3350546"],"URL":"https:\/\/doi.org\/10.1145\/3350546.3352501","relation":{},"subject":[],"published":{"date-parts":[[2019,10,14]]},"assertion":[{"value":"2019-10-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}