{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:34:50Z","timestamp":1742974490942,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030902865"},{"type":"electronic","value":"9783030902872"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-90287-2_4","type":"book-chapter","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T16:05:35Z","timestamp":1647273935000},"page":"65-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Practical Approach to Intelligent Spoken Dialogue for Third-Party Applications on Home Devices with Linear Bandits"],"prefix":"10.1007","author":[{"given":"Robin","family":"Allesiardo","sequence":"first","affiliation":[]},{"given":"Christophe","family":"Sauldubois","sequence":"additional","affiliation":[]},{"given":"Fabrice","family":"Depaulis","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Bulteau","sequence":"additional","affiliation":[]},{"given":"Fr\u00e9d\u00e9ric","family":"Chantrel","sequence":"additional","affiliation":[]},{"given":"Erwan","family":"Pigneul","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Allesiardo, R., F\u00e9raud, R., & Bouneffouf, D. (2014). A neural networks committee for the contextual bandit problem. In Neural Information Processing - 21st International Conference, ICONIP (pp. 374\u2013381).","key":"4_CR1","DOI":"10.1007\/978-3-319-12637-1_47"},{"unstructured":"Amazon (2017). Alexa skill kit.","key":"4_CR2"},{"issue":"2\u20133","key":"4_CR3","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002). Finite-time analysis of the multiarmed bandit problem. Machine Learning,\u00a047(2\u20133), 235\u2013256.","journal-title":"Machine Learning"},{"issue":"1\u20132","key":"4_CR4","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"AG Barto","year":"2003","unstructured":"Barto, A. G., & Mahadevan, S. (2003). Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems,\u00a013(1\u20132), 41\u201377.","journal-title":"Discrete Event Dynamic Systems"},{"unstructured":"Bouraoui, J.-L., & Lemaire, V. (2017). Cluster-based graphs for conceiving dialog systems. In Workshop DMNLP at European Conference on Machine Learning (ECML).","key":"4_CR5"},{"unstructured":"Chu, W., Li, L., Reyzin, L., & Schapire, R. (2011). Contextual bandits with linear payoff functions. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, volume\u00a015 of Proceedings of Machine Learning Research, pages 208\u2013214, Fort Lauderdale, FL, USA. PMLR.","key":"4_CR6"},{"doi-asserted-by":"crossref","unstructured":"Cuay\u00e1huitl, H., Renals, S., Lemon, O., & Shimodaira, H. (2010). Evaluation of a hierarchical reinforcement learning spoken dialogue system. Computer Speech and Language,\u00a024(2), 395.","key":"4_CR7","DOI":"10.1016\/j.csl.2009.07.001"},{"unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805.","key":"4_CR8"},{"doi-asserted-by":"crossref","unstructured":"Dhingra, B., Li, L., Li, X., Gao, J., Chen, Y.-N., Ahmed, F., & Deng, L. (2016). End-to-end reinforcement learning of dialogue agents for information access. Technical report.","key":"4_CR9","DOI":"10.18653\/v1\/P17-1045"},{"doi-asserted-by":"crossref","unstructured":"Fatemi, M., Asri, L.\u00a0E., Schulz, H., He, J., & Suleman, K. (2016). Policy networks with two-stage training for dialogue systems. In Proceedings of the SIGDIAL 2016 Conference, The 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 13-15 September 2016, Los Angeles, CA, USA (pp. 101\u2013110).","key":"4_CR10","DOI":"10.18653\/v1\/W16-3613"},{"unstructured":"F\u00e9raud, R., Allesiardo, R., Urvoy, T., & Cl\u00e9rot, F. (2016). Random forest for the contextual bandit problem. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS 2016, Cadiz, Spain, May 9-11, 2016 (pp. 93\u2013101).","key":"4_CR11"},{"unstructured":"Google (2017). Dialogflow.","key":"4_CR12"},{"doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016a). Bag of tricks for efficient text classification.","key":"4_CR13","DOI":"10.18653\/v1\/E17-2068"},{"doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016b). Bag of tricks for efficient text classification. arXiv:1607.01759.","key":"4_CR14","DOI":"10.18653\/v1\/E17-2068"},{"issue":"1","key":"4_CR15","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"T Lai","year":"1985","unstructured":"Lai, T., & Robbins, H. (1985). Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics,\u00a06(1), 4\u201322.","journal-title":"Advances in Applied Mathematics"},{"unstructured":"Langford, J. & Zhang, T. (2007). The epoch-greedy algorithm for multi-armed bandits with side information. In Advances in Neural Information Processing Systems 20, Proceedings of the Twenty-First Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 3-6, 2007 (pp. 817\u2013824).","key":"4_CR16"},{"doi-asserted-by":"crossref","unstructured":"Li, L., Chu, W., Langford, J., & Schapire, R.\u00a0E. (2010). A contextual-bandit approach to personalized news article recommendation. In Proceedings of the 19th International Conference on World Wide Web, WWW \u201910 (pp. 661\u2013670). New York, NY, USA: ACM.","key":"4_CR17","DOI":"10.1145\/1772690.1772758"},{"unstructured":"Microsoft (2017). Botframework.","key":"4_CR18"},{"unstructured":"Rojas-Barahona, L.\u00a0M., Gasic, M., Mrksic, N., Su, P., Ultes, S., Wen, T., Young, S.\u00a0J., & Vandyke, D. (2017). A network-based end-to-end trainable task-oriented dialogue system. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers (pp. 438\u2013449).","key":"4_CR19"},{"unstructured":"Singh, S.\u00a0P., Kearns, M.\u00a0J., Litman, D.\u00a0J., & Walker, M.\u00a0A. (1999). Reinforcement learning for spoken dialogue systems. In Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29 - December 4, 1999] (pp. 956\u2013962).","key":"4_CR20"},{"doi-asserted-by":"crossref","unstructured":"Sutton, R. S. (1988). Learning to predict by the methods of temporal differences. Machine Learning,\u00a03, 9\u201344.","key":"4_CR21","DOI":"10.1007\/BF00115009"},{"doi-asserted-by":"crossref","unstructured":"Torregrossa, F., Kooli, N., Allesiardo, R., & Pigneul, E. (2019). How we achieved a production ready slot filling deep neural network without initial natural language data. In T. Gedeon, K. W. Wong, & M. Lee (Eds.), Neural Information Processing (pp. 247\u2013255). Cham: Springer International Publishing.","key":"4_CR22","DOI":"10.1007\/978-3-030-36808-1_27"}],"container-title":["Studies in Computational Intelligence","Advances in Knowledge Discovery and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-90287-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T16:08:20Z","timestamp":1647274100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-90287-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030902865","9783030902872"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-90287-2_4","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}