{"type":"ScholarlyArticle","title":"Reinforcement Learning for Turn-Taking Management in Incremental Spoken Dialogue Systems","authors":[{"name":"Hatim Khouzaimi","slug":"hatim-khouzaimi","given":"Hatim","family":"Khouzaimi","affiliation":""},{"name":"Romain Laroche","slug":"romain-laroche","given":"Romain","family":"Laroche","affiliation":""},{"name":"Fabrice Lefèvre","slug":"fabrice-lefevre","given":"Fabrice","family":"Lefèvre","affiliation":""}],"abstract":"In this article, reinforcement learning is used to learn an optimal turn-taking strategy for vocal human-machine dialogue. The Orange Labs' Majordomo dialogue system, which allows the users to have conversations within a smart home, has been upgraded to an incremental version. First, a user simulator is built in order to generate a dialogue corpus which thereafter is used to optimise the turn-taking strategy from delayed rewards with the Fitted-Q reinforcement learning algorithm. Real users test and evaluate the new learnt strategy, versus a non-incremental and a handcrafted incremental strategies. The data-driven strategy is shown to significantly improve the task completion ratio and to be preferred by the users according to subjective metrics.","doi":null,"url":"https://ijcai.org/proceedings/2016/402","pdf":"https://ijcai.org/proceedings/2016/0402.pdf","markdown":"https://ijcai.org/proceedings/2016/402.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/402","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":402,"pages":{"first":2831,"last":2836},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}