A Two-Tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies
نویسندگان
چکیده
We present a new two-tier user simulation model for learning adaptive referring expression generation (REG) policies for spoken dialogue systems using reinforcement learning. Current user simulation models that are used for dialogue policy learning do not simulate users with different levels of domain expertise and are not responsive to referring expressions used by the system. The twotier model displays these features, that are crucial to learning an adaptive REG policy. We also show that the two-tier model simulates real user behaviour more closely than other baseline models, using the dialogue similarity measure based on Kullback-Leibler divergence.
منابع مشابه
Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to understand in technical domains where users may not know the technical ‘jargon’ names of the domain entities. In such cases, dialogue systems must be able to model the user’s (lexical) domain knowledge and use appropriate ...
متن کاملAdaptive Referring Expression Generation in Spoken Dialogue Systems: Evaluation with Real Users
We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to understand in technical domains where users may not know the technical ‘jargon’ names of the domain entities. In such cases, dialogue systems must be able to model the user’s (...
متن کاملLearning Adaptive Referring Expression Generation Policies for Spoken Dialogue Systems using Reinforcement Learning
Adaptive generation of referring expressions in dialogues is beneficial in terms of grounding between the dialogue partners. However, handcoding adaptive REG policies is hard. We present a reinforcement learning framework to automatically learn an adaptive referring expression generation policy for spoken dialogue systems.
متن کاملLearning Adaptive Referring Expression Generation Policies for Spoken Dialogue Systems
Adaptive generation of referring expressions in dialogues is beneficial in terms of grounding between the dialogue partners. However, handcoding adaptive REG policies is hard. We present a reinforcement learning framework to automatically learn an adaptive referring expression generation policy for spoken dialogue systems.
متن کاملA Wizard-of-Oz Environment to Study Referring Expression Generation in a Situated Spoken Dialogue Task
We present a Wizard-of-Oz environment for data collection on Referring Expression Generation (REG) in a real situated spoken dialogue task. The collected data will be used to build user simulation models for reinforcement learning of referring expression generation strategies.
متن کامل