[1] GORIN A L,RICCARDI G,WRIGHT J H.How may I help you?[J].Speech Communication,1997,23(1/2):113-127. [2] MCTEAR M F.Spoken dialogue technology:toward the conversational user interface[M].Berlin,Germany:Springer,2004. [3] JOKINEN K,MCTEAR M F.Spoken dialogue systems[J].Synthesis Lectures on Human Language Technologies,2009,2(1):151-170. [4] CAO Junkuo,CHEN Guolian.Human-machine dialogue system[M].Beijing:Publishing House of Eletronics Industry,2017.(in Chinese)曹均阔,陈国莲.人机对话系统[M].北京:电子工业出版社,2017. [5] CHEN Hongsen,LIU Xiaoru,YIN Dawei,et al.A survey on dialogue systems:recent advances and new frontiers[J].ACM SIGKDD Explorations Newsletter,2017,19(2):25-35. [6] Apple.Apple SIRI[EB/OL].[2019-11-30].https://www.apple.com/ios/siri/. [7] SERBAN I V,SANKAR C,GERMAIN M,et al.A deep reinforcement learning chatbot[EB/OL].[2019-11-30].https://arxiv.org/abs/1801.06700.pdf. [8] SENEFF S,HIRSCHMAN L,ZUE V W.Interactive problem solving and dialogue in the ATIS domain[C]//Proceedings of the 3rd DARPA Speech and Natural Language Workshop.[S.1.]:MIT Press,1991:653-668. [9] WALKER M,ABERDEEN J,BOLAND J,et al.DARPA communicator dialog travel planning systems:the June 2000 data collection[C]//Proceedings of the 7th European Conference on Speech Communication and Technology.Aalborg,Denmark:[s.n.],2001:1371-1374. [10] ZHAO Yangyang,WANG Zhenyu,WANG Pei,et al.A survey on task-oriented dialogue systems[J].Chinese Journal of Computers,2019,43(10):1862-1896.(in Chinese)赵阳洋,王振宇,王佩,等.任务型对话系统研究综述[J].计算机学报,2019,43(10):1862-1896. [11] WILLIAMS J D,RAUX A,HENDERSON M.The dialog state tracking challenge series:a review[J].Dialogue and Discourse,2016,7(3):4-33. [12] ZHONG Keli.Research and implementation of dialogue management system based on POMDP[D].Beijing:Beijing University of Posts and Telecommunications,2014.(in Chinese)钟可立.基于POMDP的对话管理系统研究与实现[D].北京:北京邮电大学,2014. [13] LEVIN E,PIERACCINI R,ECKERT W.Using Markov decision process for learning dialogue strategies[C]//Proceedings of International IEEE Conference on Acoustics,Speech and Signal Processing.Washington D.C.,USA:IEEE Press,1998:201-204. [14] ZHAO T,LU A,LEE K,et al.Generative encoder-decoder models for task-oriented spoken dialog systems with chatting capability[C]//Proceedings of SIGDIAL'17.Saarbrucken,Germany:[s.n.],2017:27-36. [15] VIJAYAKUMAR A K,COGSWELL M,SELVAARJU R R,et al.Diverse beam search:decoding diverse solutions from neural sequence models[EB/OL].[2019-11-30].https://arxiv.org/pdf/1610.02424.pdf. [16] LUAN Y,BROCKETT C,DOLAN B,et al.Multi-task learning for speaker-role adaptation in neural conversation models[C]//Proceedings of the 8th International Joint Conference on Natural Language Processing.Taipei,China:[s.n.],2017:605-614 [17] ZHAO Yangyang,WANG Zhenyu,YIN Kai,et al.Dynamic reward-based dueling deep dyna-q:robust policy learning in noisy environments[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2017:487-496. [18] MNIH V,KAVUKCUOGLU K,SILVER D,et al.Playing Atari with deep reinforcement learning[C]//Proceedings of the 26th Workshops on Neural Information Processing Systems.Lake Tahoe,USA:[s.n.],2013:201-220. [19] MNIH V,KAVUKCUOGLU K,SILVER D,et al.Human-level control through deep reinforcement learning[J].Nature,2015,518(7540):529-533. [20] LARDDON S,TRAUM D R.Information state and dialogue management in the TRINDI dialogue move engine toolkit[J].Natural Language Engineering,2000,6(3):323-340. [21] TRAUM D R,LARSSON S.The information state approach to dialogue management[M].Berlin,Germany:Springer,2003. |