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

TL;DR

This paper presents a multi-dimensional dialogue management approach that leverages transfer learning to improve training efficiency and performance in new dialogue domains with limited data.

Contribution

It introduces a multi-dimensional adaptation method for dialogue policies that enhances transfer learning for extended action sets in spoken dialogue systems.

Findings

Multi-dimensional adaptation improves performance with limited data.

Proposed method outperforms baseline by 7% in success rate.

Effective transfer learning reduces training time for new domains.

Abstract

A major bottleneck for building statistical spoken dialogue systems for new domains and applications is the need for large amounts of training data. To address this problem, we adopt the multi-dimensional approach to dialogue management and evaluate its potential for transfer learning. Specifically, we exploit pre-trained task-independent policies to speed up training for an extended task-specific action set, in which the single summary action for requesting a slot is replaced by multiple slot-specific request actions. Policy optimisation and evaluation experiments using an agenda-based user simulator show that with limited training data, much better performance levels can be achieved when using the proposed multi-dimensional adaptation method. We confirm this improvement in a crowd-sourced human user evaluation of our spoken dialogue system, comparing partially trained policies. The multi-dimensional system (with adaptation on limited training data in the target scenario) outperforms the one-dimensional baseline (without adaptation on the same amount of training data) by 7% perceived success rate.