FLoReS: A Forward Looking, Reward Seeking, Dialogue Manager
نویسندگان
چکیده
We present FLoReS, a new information-state based dialogue manager, making use of forward inference, local dialogue structure, and plan operators representing sub-dialogue structure. The aim is to support both advanced, flexible, mixed initiative interaction and efficient policy creation by domain experts. The dialogue manager has been used for two characters in the SimCoach project, and is currently being used in several related projects. We present the design of the dialogue manager and preliminary comparative evaluation with a previous system that uses a more conventional state chart dialogue manager.
منابع مشابه
A Mixed-Initiative Conversational Dialogue System for Healthcare
We present a mixed initiative conversational dialogue system designed to address primarily mental health care concerns related to military deployment. It is supported by a new information-state based dialogue manager, FLoReS (Forward-Looking, Reward Seeking dialogue manager), that allows both advanced, flexible, mixed initiative interaction, and efficient policy creation by domain experts. To e...
متن کاملDeep Reinforcement Learning for Dialogue Generation
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes. Modeling the future direction of a dialogue is crucial to generating coherent, interesting dialogues, a need which led traditional NLP models of dialogue to draw on ...
متن کاملInteractive reinforcement learning for task-oriented dialogue management
Dialogue management is the component of a dialogue system that determines the optimal action for the system to take at each turn. An important consideration for dialogue managers is the ability to adapt to new user behaviors unseen during training. In this paper, we investigate policy gradient based methods for interactive reinforcement learning where the agent receives action-specific feedback...
متن کاملTask Completion Transfer Learning for Reward Inference
Reinforcement learning-based spoken dialogue systems aim to compute an optimal strategy for dialogue management from interactions with users. They compare their different management strategies on the basis of a numerical reward function. Reward inference consists of learning a reward function from dialogues scored by users. A major issue for reward inference algorithms is that important paramet...
متن کاملMaking Sense of Partial ∗
We address the challenging task of processing partial multimodal utterances in a mixed-initiative dialogue system for multiple applications such as information seeking, device control etc. Based on four different types of expectations computed by our action planner (aka dialog manager), we distinguish between expected utterances, various degrees of unexpected but plausible utterances, and unint...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014