DeepAI AI Chat
Log In Sign Up

User Evaluation of a Multi-dimensional Statistical Dialogue System

by   Simon Keizer, et al.
Charles University in Prague
Heriot-Watt University

We present the first complete spoken dialogue system driven by a multi-dimensional statistical dialogue manager. This framework has been shown to substantially reduce data needs by leveraging domain-independent dimensions, such as social obligations or feedback, which (as we show) can be transferred between domains. In this paper, we conduct a user study and show that the performance of a multi-dimensional system, which can be adapted from a source domain, is equivalent to that of a one-dimensional baseline, which can only be trained from scratch.


Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling

Recent statistical approaches have improved the robustness and scalabili...

Dialogue Strategy Adaptation to New Action Sets Using Multi-dimensional Modelling

A major bottleneck for building statistical spoken dialogue systems for ...

Adaptive Nonparametric Psychophysics

We introduce a new set of models and adaptive psychometric testing metho...

Identifying Data And Information Streams In Cyberspace: A Multi-Dimensional Perspective

Cyberspace has gradually replaced the physical reality, its role evolvin...

Enabling Dialogue Management with Dynamically Created Dialogue Actions

In order to take up the challenge of realising user-adaptive system beha...

Multi-Dimensional Unlimited Sampling and Robust Reconstruction

In this paper we introduce a new sampling and reconstruction approach fo...