Dialogue policy learning(DPL)is a key component in a task-oriented dialogue(TOD)system.Its goal is to decide the next action of the dialogue system,given the dialogue state at each turn based on a learned dialogue pol...Dialogue policy learning(DPL)is a key component in a task-oriented dialogue(TOD)system.Its goal is to decide the next action of the dialogue system,given the dialogue state at each turn based on a learned dialogue policy.Reinforcement learning(RL)is widely used to optimize this dialogue policy.In the learning process,the user is regarded as the environment and the system as the agent.In this paper,we present an overview of the recent advances and challenges in dialogue policy from the perspective of RL.More specifically,we identify the problems and summarize corresponding solutions for RL-based dialogue policy learning.In addition,we provide a comprehensive survey of applying RL to DPL by categorizing recent methods into five basic elements in RL.We believe this survey can shed light on future research in DPL.展开更多
The goal of this presentation is to examine the hypothesis that the ethno-political conflict in Israel can be utilized in history education to foster learning of historical thinking and to construct a tolerant space w...The goal of this presentation is to examine the hypothesis that the ethno-political conflict in Israel can be utilized in history education to foster learning of historical thinking and to construct a tolerant space within the education system that will enable the structuring of in-principle criteria for coexistence prior to the ending of the conflict. I assumed that inculcation of historical knowledge in the education system in Israel by means of an attentive and reflexive cultural dialogue, which sensitively and skillfully confronts contradictory historical narratives as an everyday learning reality in class, will help structure a conciliatory consciousness of the kind we seek.展开更多
基金Innovation and Technology Fund(ITF),Government of the Hong Kong Special Administrative Region(HKSAR),China(No.PRP-054-21FX).
文摘Dialogue policy learning(DPL)is a key component in a task-oriented dialogue(TOD)system.Its goal is to decide the next action of the dialogue system,given the dialogue state at each turn based on a learned dialogue policy.Reinforcement learning(RL)is widely used to optimize this dialogue policy.In the learning process,the user is regarded as the environment and the system as the agent.In this paper,we present an overview of the recent advances and challenges in dialogue policy from the perspective of RL.More specifically,we identify the problems and summarize corresponding solutions for RL-based dialogue policy learning.In addition,we provide a comprehensive survey of applying RL to DPL by categorizing recent methods into five basic elements in RL.We believe this survey can shed light on future research in DPL.
文摘The goal of this presentation is to examine the hypothesis that the ethno-political conflict in Israel can be utilized in history education to foster learning of historical thinking and to construct a tolerant space within the education system that will enable the structuring of in-principle criteria for coexistence prior to the ending of the conflict. I assumed that inculcation of historical knowledge in the education system in Israel by means of an attentive and reflexive cultural dialogue, which sensitively and skillfully confronts contradictory historical narratives as an everyday learning reality in class, will help structure a conciliatory consciousness of the kind we seek.
