Dialogue Policy Learning for combinations of Noise and User Simulation: transfer results
نویسندگان
چکیده
Once a dialogue strategy has been learned for a particular set of conditions, we need to know how well it will perform when deployed in different conditions to those it was specifically trained for, i.e. how robust it is in transfer to different conditions. We first present novel learning results for different ASR noise models combined with different user simulations. We then show that policies trained in high-noise conditions perform significantly better than those trained for lownoise conditions, even when deployed in low-noise environments.
منابع مشابه
User and Noise Adaptive Dialogue Management Using Hybrid System Actions
In recent years reinforcement-learning-based approaches have been widely used for management policy optimization in spoken dialogue systems (SDS). A dialogue management policy is a mapping from dialogue states to system actions, i.e. given the state of the dialogue the dialogue policy determines the next action to be performed by the dialogue manager. So-far policy optimization primarily focuse...
متن کاملLearning dialogue strategies for interactive database search
We show how to learn optimal dialogue policies for a wide range of database search applications, concerning how many database search results to present to the user, and when to present them. We use Reinforcement Learning methods for a wide spectrum of different database simulations, turn penalty conditions, and noise conditions. Our objective is to show that our policy learning framework covers...
متن کاملOn-line Dialogue Policy Learning with Companion Teaching
On-line dialogue policy learning is the key for building evolvable conversational agent in real world scenarios. Poor initial policy can easily lead to bad user experience and consequently fail to attract sufficient real users for policy training. We propose a novel framework, companion teaching, to include a human teacher in the on-line dialogue policy training loop to address the cold start p...
متن کاملA Two-Tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies
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 mode...
متن کاملBehavior Specific User Simulation in Spoken Dialogue Systems
Spoken dialogue systems provide an opportunity for man machine interaction using spoken language as the medium of interaction. In recent years reinforcement learning-based dialogue policy optimization has evolved to be state of the art. In order to cope with the data requirement for policy optimization and also to evaluate dialogue policies user simulators are introduced. Almost all existing da...
متن کامل