Addressing Objects and Their Relations: The Conversational Entity Dialogue Model

by   Stefan Ultes, et al.
University of Cambridge

Statistical spoken dialogue systems usually rely on a single- or multi-domain dialogue model that is restricted in its capabilities of modelling complex dialogue structures, e.g., relations. In this work, we propose a novel dialogue model that is centred around entities and is able to model relations as well as multiple entities of the same type. We demonstrate in a prototype implementation benefits of relation modelling on the dialogue level and show that a trained policy using these relations outperforms the multi-domain baseline. Furthermore, we show that by modelling the relations on the dialogue level, the system is capable of processing relations present in the user input and even learns to address them in the system response.


page 2

page 11


Interactivism in Spoken Dialogue Systems

The interactivism model introduces a dynamic approach to language, commu...

LD-SDS: Towards an Expressive Spoken Dialogue System based on Linked-Data

In this work we discuss the related challenges and describe an approach ...

Enabling Dialogue Management with Dynamically Created Dialogue Actions

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

MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert

How to build a high-quality multi-domain dialogue system is a challengin...

Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling

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

Coherence Models for Dialogue

Coherence across multiple turns is a major challenge for state-of-the-ar...

Few-Shot Generalization Across Dialogue Tasks

Machine-learning based dialogue managers are able to learn complex behav...

Please sign up or login with your details

Forgot password? Click here to reset