High-Quality Diversification for Task-Oriented Dialogue Systems

06/02/2021
by   Zhiwen Tang, et al.
7

Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn policies that respond to the user appropriately and complete the tasks successfully. Training DRL agents with diverse dialogue trajectories prepare them well for rare user requests and unseen situations. One effective diversification method is to let the agent interact with a diverse set of learned user models. However, trajectories created by these artificial user models may contain generation errors, which can quickly propagate into the agent's policy. It is thus important to control the quality of the diversification and resist the noise. In this paper, we propose a novel dialogue diversification method for task-oriented dialogue systems trained in simulators. Our method, Intermittent Short Extension Ensemble (I-SEE), constrains the intensity to interact with an ensemble of diverse user models and effectively controls the quality of the diversification. Evaluations on the Multiwoz dataset show that I-SEE successfully boosts the performance of several state-of-the-art DRL dialogue agents.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/22/2020

Deep Reinforcement Learning for On-line Dialogue State Tracking

Dialogue state tracking (DST) is a crucial module in dialogue management...
research
08/27/2019

Ensemble-Based Deep Reinforcement Learning for Chatbots

Trainable chatbots that exhibit fluent and human-like conversations rema...
research
11/10/2017

Integrating User and Agent Models: A Deep Task-Oriented Dialogue System

Task-oriented dialogue systems can efficiently serve a large number of c...
research
05/27/2019

AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning

Dialogue policy plays an important role in task-oriented spoken dialogue...
research
10/24/2022

Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?

Task-oriented dialogue (TOD) systems have assisted users on many tasks, ...
research
11/25/2015

Strategic Dialogue Management via Deep Reinforcement Learning

Artificially intelligent agents equipped with strategic skills that can ...
research
06/12/2019

Incremental Learning from Scratch for Task-Oriented Dialogue Systems

Clarifying user needs is essential for existing task-oriented dialogue s...

Please sign up or login with your details

Forgot password? Click here to reset