Policy Activation for Open-Ended Dialogue Management
نویسندگان
چکیده
An important difficulty in developing spoken dialogue systems for robots is the open-ended nature of most interactions. Robotic agents must typically operate in complex, continuously changing environments which are difficult to model and do not provide any clear, predefined goal. Directly capturing this complexity in a single, large dialogue policy is thus inadequate. This paper presents a new approach which tackles the complexity of open-ended interactions by breaking it into a set of small, independent policies, which can be activated and deactivated at runtime by a dedicated mechanism. The approach is currently being implemented in a spoken dialogue system for autonomous robots.
منابع مشابه
Enabling Reinforcement Learning for Open Dialogue Systems through Speech Stress Detection
The human speech signal contains a wide range of paralinguistic information and the interpretation and exploitation of this information presents a fascinating challenge. This paper seeks to demonstrate that emotion is central to the construction of an openended dialogue system. Emotion forms a useful, practical, metric that enables a agent to both maintain a user’s positive emotional state and ...
متن کاملMulti-Policy Dialogue Management
We present a new approach to dialogue management based on the use of multiple, interconnected policies. Instead of capturing the complexity of the interaction in a single large policy, the dialogue manager operates with a collection of small local policies combined concurrently and hierarchically. The metacontrol of these policies relies on an activation vector updated before and after each turn.
متن کاملPerspectives on health policy dialogue: definition, perceived importance and coordination
BACKGROUND Countries in the World Health Organization African Region have witnessed an increase in global health initiatives in the recent past. Although these have provided opportunities for expanding coverage of health interventions; their poor alignment with the countries' priorities and weak coordination, are among the challenges that have affected their impact. A well-coordinated health po...
متن کاملGoal-driven approach to open-ended dialogue management using BDI agents
We describe a BDI (Belief, Desire, Intention) approach and architecture for a conversational virtual companion embodied as a child’s Toy. Our aim is to support both structured conversation-based activities (e.g., story-telling, collaborative games) as well as more free-flowing, engaging dialogue with variation and some unpredictability. We argue that a goal-oriented approach to the agent’s conv...
متن کاملLearning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings
We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both str...
متن کامل