{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:34:01Z","timestamp":1743039241003,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030862299"},{"type":"electronic","value":"9783030862305"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86230-5_49","type":"book-chapter","created":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T09:03:00Z","timestamp":1631005380000},"page":"625-634","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["One Arm to Rule Them All: Online Learning with Multi-armed Bandits for Low-Resource Conversational Agents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5729-7608","authenticated-orcid":false,"given":"V\u00e2nia","family":"Mendon\u00e7a","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2456-5028","authenticated-orcid":false,"given":"Lu\u00edsa","family":"Coheur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5782-3142","authenticated-orcid":false,"given":"Alberto","family":"Sardinha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,3]]},"reference":[{"issue":"2\u20133","key":"49_CR1","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.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2\u20133), 235\u2013256 (2002). https:\/\/doi.org\/10.1023\/A:1013689704352","journal-title":"Mach. Learn."},{"key":"49_CR2","doi-asserted-by":"publisher","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: Gambling in a rigged casino: the adversarial multi-armed bandit problem. In: Annual Symposium on Foundations of Computer Science - Proceedings, pp. 322\u2013331 (1995). https:\/\/doi.org\/10.1109\/sfcs.1995.492488","DOI":"10.1109\/sfcs.1995.492488"},{"key":"49_CR3","unstructured":"Banchs, R.E., Li, H.: Iris: a chat-oriented dialogue system based on the vector space model. In: Proceedings of the ACL 2012 System Demonstrations, ACL 2012, pp. 37\u201342. Association for Computational Linguistics, Stroudsburg (2012). http:\/\/dl.acm.org\/citation.cfm?id=2390470.2390477"},{"key":"49_CR4","unstructured":"Biermann, A.W., Long, P.M.: The composition of messages in speech-graphics interactive systems. In: International Symposium on Spoken Dialogue, pp. 97\u2013100 (1996). http:\/\/citeseerx.ist.psu.edu\/viewdoc\/download?doi=10.1.1.55.721&rep=rep1&type=pdf"},{"key":"49_CR5","unstructured":"Boussaha, B.E.A., Hernandez, N., Jacquin, C., Morin, E.: Deep Retrieval-Based Dialogue Systems: A Short Review. Technical report (2019). http:\/\/arxiv.org\/abs\/1907.12878"},{"key":"49_CR6","doi-asserted-by":"publisher","unstructured":"Brill, E., Dumais, S., Banko, M.: An analysis of the askmsr question-answering system. In: Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing - Volume 10, EMNLP 2002, pp. 257\u2013264. Association for Computational Linguistics, USA (2002). https:\/\/doi.org\/10.3115\/1118693.1118726, https:\/\/doi.org\/10.3115\/1118693.1118726","DOI":"10.3115\/1118693.1118726"},{"key":"49_CR7","doi-asserted-by":"crossref","unstructured":"Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning and Games. Cambridge University Press, Cambridge (2006)","DOI":"10.1017\/CBO9780511546921"},{"key":"49_CR8","doi-asserted-by":"publisher","unstructured":"Chen, Q., Wang, W.: Sequential neural networks for noetic end-to-end response selection. In: Proceedings of the 7th Dialog System Technology Challenge (DSTC7) (2019). https:\/\/doi.org\/10.1016\/j.csl.2020.101072","DOI":"10.1016\/j.csl.2020.101072"},{"key":"49_CR9","doi-asserted-by":"publisher","unstructured":"Ga\u0161i\u0107, M., Jur\u010di\u010dek, F., Thomson, B., Yu, K., Young, S.: On-line policy optimisation of spoken dialogue systems via live interaction with human subjects. In: 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings, pp. 312\u2013317 (2011). https:\/\/doi.org\/10.1109\/ASRU.2011.6163950","DOI":"10.1109\/ASRU.2011.6163950"},{"key":"49_CR10","unstructured":"Genevay, A., Laroche, R.: Transfer learning for user adaptation in spoken dialogue systems. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, pp. 975\u2013983 (2016)"},{"issue":"2","key":"49_CR11","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","volume":"11","author":"P Jaccard","year":"1912","unstructured":"Jaccard, P.: The distribution of the flora in the alpine zone. New Phytol. 11(2), 37\u201350 (1912)","journal-title":"New Phytol."},{"issue":"1","key":"49_CR12","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"TL Lai","year":"1985","unstructured":"Lai, T.L., Robbins, H.: Asymptotically efficient adaptive allocation rules. Adv. Appl. Math. 6(1), 4\u201322 (1985). https:\/\/doi.org\/10.1016\/0196-8858(85)90002-8","journal-title":"Adv. Appl. Math."},{"key":"49_CR13","doi-asserted-by":"crossref","unstructured":"Levin, E., Pieraccini, R., Eckert, W.: A stochastic model of human-machine interaction for learning dialog strategies. IEEE Trans. Speech Audio Process. 8 (2000)","DOI":"10.1109\/89.817450"},{"key":"49_CR14","doi-asserted-by":"publisher","unstructured":"Lin, J.: An exploration of the principles underlying redundancy-based factoid question answering. ACM Trans. Inf. Syst. 25(2), 6-es (2007). https:\/\/doi.org\/10.1145\/1229179.1229180. https:\/\/doi.org\/10.1145\/1229179.1229180","DOI":"10.1145\/1229179.1229180"},{"key":"49_CR15","doi-asserted-by":"crossref","unstructured":"Liu, B., Yu, T., Lane, I., Mengshoel, O.J.: Customized nonlinear bandits for online response selection in neural conversation models. In: The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), pp. 5245\u20135252 (2018)","DOI":"10.1609\/aaai.v32i1.12028"},{"key":"49_CR16","unstructured":"Magarreiro, D., Coheur, L., Melo, F.S.: Using subtitles to deal with out-of-domain interactions. In: SemDial 2014 - DialWatt (2014)"},{"key":"49_CR17","unstructured":"McCandless, M., Hatcher, E., Gospodnetic, O.: Lucene in Action, Second Edition: Covers Apache Lucene 3.0. Manning Publications Co., Greenwich, CT, USA (2010)"},{"key":"49_CR18","unstructured":"Mendon\u00e7a, V., Melo, F.S., Coheur, L., Sardinha, A.: A Conversational Agent Powered by Online Learning, vol. 3, pp. 1637\u20131639. International Foundation for Autonomous Agents and Multiagent Systems, S\u00e3o Paulo, Brazil (2017). http:\/\/dl.acm.org\/citation.cfm?id=3091282.3091388"},{"key":"49_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1007\/978-3-319-65340-2_60","volume-title":"Progress in Artificial Intelligence","author":"V Mendon\u00e7a","year":"2017","unstructured":"Mendon\u00e7a, V., Melo, F.S., Coheur, L., Sardinha, A.: Online learning for conversational agents. In: Oliveira, E., Gama, J., Vale, Z., Lopes Cardoso, H. (eds.) EPIA 2017. LNCS (LNAI), vol. 10423, pp. 739\u2013750. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-65340-2_60"},{"key":"49_CR20","unstructured":"Oliveira, H.G., et al.: AIA-BDE: a corpus of FAQs in Portuguese and their variations. In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pp. 5442\u20135449 (2020)"},{"issue":"5","key":"49_CR21","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1090\/S0002-9904-1952-09620-8","volume":"58","author":"H Robbins","year":"1952","unstructured":"Robbins, H.: Some aspects of the sequential design of experiments. Bull. Am. Math. Soc. 58(5), 527\u2013535 (1952). https:\/\/doi.org\/10.1090\/S0002-9904-1952-09620-8","journal-title":"Bull. Am. Math. Soc."},{"key":"49_CR22","unstructured":"Roller, S., et al.: Recipes for building an open-domain chatbot. Technical report (2020). http:\/\/arxiv.org\/abs\/2004.13637"},{"key":"49_CR23","unstructured":"Serban, I.V., et al.: A deep reinforcement learning chatbot. Technical report (2018)"},{"key":"49_CR24","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1613\/jair.859","volume":"16","author":"S Singh","year":"2002","unstructured":"Singh, S., Litman, D., Kearns, M., Walker, M.: Optimizing dialogue management with reinforcement learning: Experiments with the njfun system. J. Artif. Intell. Res. 16, 105\u2013133 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"49_CR25","doi-asserted-by":"publisher","unstructured":"Su, P.H., et al.: On-line active reward learning for policy optimisation in spoken dialogue systems. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2431\u20132441. Association for Computational Linguistics (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1230, http:\/\/aclweb.org\/anthology\/P16-1230","DOI":"10.18653\/v1\/P16-1230"},{"key":"49_CR26","unstructured":"Upadhyay, S., Agarwal, M., Bounneffouf, D., Khazaeni, Y.: A bandit approach to posterior dialog orchestration under a budget. In: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) (2018)"},{"issue":"3","key":"49_CR27","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1109\/TAC.2005.844079","volume":"50","author":"CC Wang","year":"2005","unstructured":"Wang, C.C., Kulkarni, S.R., Poor, H.V.: Bandit problems with side observations. IEEE Trans. Autom. Control 50(3), 338\u2013355 (2005). https:\/\/doi.org\/10.1109\/TAC.2005.844079","journal-title":"IEEE Trans. Autom. Control"},{"key":"49_CR28","doi-asserted-by":"crossref","unstructured":"Yu, Z., Xu, Z., Black, A.W., Rudnicky, A.I.: Strategy and policy learning for non-task-oriented conversational systems. In: Proceedings of the SIGDIAL 2016 Conference, pp. 404\u2013412 (2016)","DOI":"10.18653\/v1\/W16-3649"},{"key":"49_CR29","unstructured":"Zhang, Z., Li, J., Zhu, P., Zhao, H., Liu, G.: Modeling multi-turn conversation with deep utterance aggregation. In: Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018), pp. 3740\u20133752 (2018). http:\/\/arxiv.org\/abs\/1806.09102"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86230-5_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T19:26:21Z","timestamp":1673205981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86230-5_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030862299","9783030862305"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86230-5_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"3 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.appia.pt\/epia2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"108","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"57% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.47","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.36","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}