Learning Robust Dialog Policies in Noisy Environments

12/11/2017
by   Maryam Fazel-Zarandi, et al.
0

Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural language understanding (NLU) errors. In this paper, we focus on learning robust dialog policies to recover from these errors. To this end, we develop a user simulator which interacts with the assistant through voice commands in realistic scenarios with noisy audio, and use it to learn dialog policies through deep reinforcement learning. We show that dialogs generated by our simulator are indistinguishable from human generated dialogs, as determined by human evaluators. Furthermore, preliminary experimental results show that the learned policies in noisy environments achieve the same execution success rate with fewer dialog turns compared to fixed rule-based policies.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/08/2019

Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery

Training dialog policies for speech-based virtual assistants requires a ...
research
04/27/2015

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution

In this paper, we present a probabilistic framework for goal-driven spok...
research
06/10/2020

Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors

Speech-based virtual assistants, such as Amazon Alexa, Google assistant,...
research
08/02/2017

Deep Reinforcement Learning for Inquiry Dialog Policies with Logical Formula Embeddings

This paper is the first attempt to learn the policy of an inquiry dialog...
research
12/10/2021

Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems

As more users across the world are interacting with dialog agents in the...
research
04/23/2020

Learning Dialog Policies from Weak Demonstrations

Deep reinforcement learning is a promising approach to training a dialog...
research
11/17/2014

Relations World: A Possibilistic Graphical Model

We explore the idea of using a "possibilistic graphical model" as the ba...

Please sign up or login with your details

Forgot password? Click here to reset