{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T11:47:11Z","timestamp":1724672831046},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"28-29","license":[{"start":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T00:00:00Z","timestamp":1593648000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T00:00:00Z","timestamp":1593648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s11042-020-09070-7","type":"journal-article","created":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T18:04:27Z","timestamp":1593713067000},"page":"35025-35050","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A hierarchical approach for efficient multi-intent dialogue policy learning"],"prefix":"10.1007","volume":"80","author":[{"given":"Tulika","family":"Saha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhawal","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pushpak","family":"Bhattacharyya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,7,2]]},"reference":[{"key":"9070_CR1","doi-asserted-by":"crossref","unstructured":"Arulkumaran K, Deisenroth MP, Brundage M, Bharath AA (2017) A brief survey of deep reinforcement learning. arXiv:1708.05866","DOI":"10.1109\/MSP.2017.2743240"},{"key":"9070_CR2","unstructured":"Bordes A, Boureau YL, Weston J (2016) Learning end-to-end goal-oriented dialog. arXiv:1605.07683"},{"key":"9070_CR3","doi-asserted-by":"publisher","unstructured":"Budzianowski P, Ultes S, Su P, Mrksic N, Wen T, Casanueva I, Rojas-Barahona LM, Gasic M (2017) Sub-domain modelling for dialogue management with hierarchical reinforcement learning. In: Proceedings of the 18th annual SIGdial meeting on discourse and dialogue, Saarbr\u00fccken, Germany, August 15-17, 2017. https:\/\/doi.org\/10.18653\/v1\/w17-5512, pp 86\u201392","DOI":"10.18653\/v1\/w17-5512"},{"key":"9070_CR4","doi-asserted-by":"crossref","unstructured":"Casanueva I, Budzianowski P, Su P, Ultes S, Rojas-Barahona LM, Tseng B, Gasic M (2018) Feudal reinforcement learning for dialogue management in large domains. In: Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies, NAACL-HLT, New Orleans, Louisiana, USA, June 1-6, 2018, vol 2 (Short Papers). https:\/\/aclanthology.info\/papers\/N18-2112\/n18-2112, pp 714\u2013719","DOI":"10.18653\/v1\/N18-2112"},{"key":"9070_CR5","doi-asserted-by":"crossref","unstructured":"Cuay\u00e1huitl H (2017) Simpleds: a simple deep reinforcement learning dialogue system. In: Dialogues with social robots. Springer, pp 109\u2013118","DOI":"10.1007\/978-981-10-2585-3_8"},{"key":"9070_CR6","unstructured":"Cuay\u00e1huitl H, Keizer S, Lemon O (2015) Strategic dialogue management via deep reinforcement learning. arXiv:1511.08099"},{"key":"9070_CR7","doi-asserted-by":"crossref","unstructured":"Cuay\u00e1huitl H, Yu S, Williamson A, Carse J (2016) Deep reinforcement learning for multi-domain dialogue systems. arXiv:1611.08675","DOI":"10.1109\/IJCNN.2017.7966275"},{"key":"9070_CR8","doi-asserted-by":"crossref","unstructured":"Cuay\u00e1huitl H, Yu S, et al. (2017) Deep reinforcement learning of dialogue policies with less weight updates","DOI":"10.21437\/Interspeech.2017-1060"},{"key":"9070_CR9","unstructured":"Fazel-Zarandi M, Li SW, Cao J, Casale J, Henderson P, Whitney D, Geramifard A (2017) Learning robust dialog policies in noisy environments. arXiv:1712.04034"},{"key":"9070_CR10","unstructured":"Fraser N (1998) Assessment of interactive systems. In: Handbook of standards and resources for spoken language systems. Mouton de Gruyter, pp 564\u2013615"},{"issue":"8","key":"9070_CR11","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computation 9(8):1735\u20131780","journal-title":"Neural Computation"},{"key":"9070_CR12","doi-asserted-by":"publisher","unstructured":"Ilievski V, Musat C, Hossmann A, Baeriswyl M (2018) Goal-oriented chatbot dialog management bootstrapping with transfer learning. In: Proceedings of the twenty-seventh international joint conference on artificial intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden. https:\/\/doi.org\/10.24963\/ijcai.2018\/572, pp 4115\u20134121","DOI":"10.24963\/ijcai.2018\/572"},{"key":"9070_CR13","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. Journal of Artificial Intelligence Research 4:237\u2013285","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9070_CR14","doi-asserted-by":"crossref","unstructured":"Keizer S, Guhe M, Cuay\u00e1huitl H, Efstathiou I, Engelbrecht KP, Dobre M, Lascarides A, Lemon O (2017) Evaluating persuasion strategies and deep reinforcement learning methods for negotiation dialogue agents. In: Proceedings of the 15th conference of the European chapter of the association for computational linguistics: Volume 2, Short Papers, vol 2, pp 480\u2013484","DOI":"10.18653\/v1\/E17-2077"},{"key":"9070_CR15","doi-asserted-by":"crossref","unstructured":"Levin E, Pieraccini R, Eckert W (1998) Using markov decision process for learning dialogue strategies. In: Proceedings of the 1998 IEEE international conference on acoustics, speech and signal processing, 1998, vol 1. IEEE, pp 201\u2013204","DOI":"10.1109\/ICASSP.1998.674402"},{"key":"9070_CR16","unstructured":"Li X, Chen YN, Li L, Gao J, Celikyilmaz A (2017) End-to-end task-completion neural dialogue systems. arXiv:1703.01008"},{"key":"9070_CR17","doi-asserted-by":"crossref","unstructured":"Lipton Z, Li X, Gao J, Li L, Ahmed F, Deng L (2018) Bbq-networks: efficient exploration in deep reinforcement learning for task-oriented dialogue systems. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11946"},{"key":"9070_CR18","doi-asserted-by":"crossref","unstructured":"McTear MF (1998) Modelling spoken dialogues with state transition diagrams: experiences with the cslu toolkit. In: Fifth international conference on spoken language processing","DOI":"10.21437\/ICSLP.1998-92"},{"issue":"1","key":"9070_CR19","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1145\/505282.505285","volume":"34","author":"MF McTear","year":"2002","unstructured":"McTear MF (2002) Spoken dialogue technology: enabling the conversational user interface. ACM Computing Surveys (CSUR) 34(1):90\u2013169","journal-title":"ACM Computing Surveys (CSUR)"},{"issue":"3","key":"9070_CR20","doi-asserted-by":"publisher","first-page":"110","DOI":"10.3390\/data4030110","volume":"4","author":"TL Meng","year":"2019","unstructured":"Meng TL, Khushi M (2019) Reinforcement learning in financial markets. Data 4(3):110. https:\/\/doi.org\/10.3390\/data4030110","journal-title":"Data"},{"key":"9070_CR21","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv:1312.5602"},{"key":"9070_CR22","doi-asserted-by":"crossref","unstructured":"Peng B, Li X, Li L, Gao J, \u00c7elikyilmaz A, Lee S, Wong K (2017) Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning. In: Proceedings of the 2017 conference on empirical methods in natural language processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017. https:\/\/aclanthology.info\/papers\/D17-1237\/d17-1237, pp 2231\u20132240","DOI":"10.18653\/v1\/D17-1237"},{"key":"9070_CR23","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"9070_CR24","doi-asserted-by":"crossref","unstructured":"Price PJ (1990) Evaluation of spoken language systems: the atis domain. In: Speech and natural language: proceedings of a workshop held at Hidden Valley, Pennsylvania, June 24-27, 1990","DOI":"10.3115\/116580.116612"},{"key":"9070_CR25","doi-asserted-by":"crossref","unstructured":"Saha T, Gupta D, Saha S, Bhattacharyya P (2018) Neural information processing. In: Cheng L, Leung ACS, Ozawa S (eds), Berlin, pp 359\u2013372","DOI":"10.1007\/978-3-030-04182-3_32"},{"key":"9070_CR26","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv:1511.05952"},{"key":"9070_CR27","doi-asserted-by":"crossref","unstructured":"Serban IV, Sordoni A, Bengio Y, Courville AC, Pineau J (2016) Building end-to-end dialogue systems using generative hierarchical neural network models. In: AAAI, vol 16, pp 3776\u20133784","DOI":"10.1609\/aaai.v30i1.9883"},{"key":"9070_CR28","volume-title":"Reinforcement learning: an introduction, vol 1","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction, vol 1. MIT Press, Cambridge"},{"key":"9070_CR29","doi-asserted-by":"crossref","unstructured":"Tang D, Li X, Gao J, Wang C, Li L, Jebara T (2018) Subgoal discovery for hierarchical dialogue policy learning. In: Proceedings of the 2018 conference on empirical methods in natural language processing, Brussels, Belgium, October 31 - November 4, 2018. https:\/\/aclanthology.info\/papers\/D18-1253\/d18-1253, pp 2298\u20132309","DOI":"10.18653\/v1\/D18-1253"},{"key":"9070_CR30","doi-asserted-by":"crossref","unstructured":"Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: AAAI, vol 16, pp 2094\u20132100","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"9070_CR31","doi-asserted-by":"crossref","unstructured":"Wen TH, Vandyke D, Mrksic N, Gasic M, Rojas-Barahona LM, Su PH, Ultes S, Young S (2016) A network-based end-to-end trainable task-oriented dialogue system. arXiv:1604.04562","DOI":"10.18653\/v1\/E17-1042"},{"key":"9070_CR32","doi-asserted-by":"crossref","unstructured":"Xu P, Sarikaya R (2013) Exploiting shared information for multi-intent natural language sentence classification. In: INTERSPEECH 2013, 14th annual conference of the international speech communication association, Lyon, France, August 25-29, 2013. http:\/\/www.isca-speech.org\/archive\/interspeech_2013\/i13_3785.html, pp 3785\u20133789","DOI":"10.21437\/Interspeech.2013-599"},{"key":"9070_CR33","doi-asserted-by":"crossref","unstructured":"Zhao T, Eskenazi M (2016) Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning. arXiv:1606.02560","DOI":"10.18653\/v1\/W16-3601"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09070-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09070-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09070-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T09:57:01Z","timestamp":1696327021000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09070-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,2]]},"references-count":33,"journal-issue":{"issue":"28-29","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["9070"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09070-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,2]]},"assertion":[{"value":"3 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}