Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

TL;DR

This paper introduces TRADE, a transferable dialogue state generator that improves multi-domain task-oriented dialogue systems by effectively handling unknown slot values and adapting to new domains with minimal data.

Contribution

The paper presents a novel transfer learning approach for dialogue state tracking that leverages a copy mechanism and shared components to enable zero-shot and few-shot domain adaptation.

Findings

Achieves 48.62% joint goal accuracy on MultiWOZ dataset.

Demonstrates effective zero-shot transfer with 60.58% accuracy.

Adapts to few-shot scenarios without forgetting previous domains.

Abstract

Over-dependence on domain ontology and lack of knowledge sharing across domains are two practical and yet less studied problems of dialogue state tracking. Existing approaches generally fall short in tracking unknown slot values during inference and often have difficulties in adapting to new domains. In this paper, we propose a Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using a copy mechanism, facilitating knowledge transfer when predicting (domain, slot, value) triplets not encountered during training. Our model is composed of an utterance encoder, a slot gate, and a state generator, which are shared across domains. Empirical results demonstrate that TRADE achieves state-of-the-art joint goal accuracy of 48.62% for the five domains of MultiWOZ, a human-human dialogue dataset. In addition, we show its transferring ability by simulating zero-shot and few-shot dialogue state tracking for unseen domains. TRADE achieves 60.58% joint goal accuracy in one of the zero-shot domains, and is able to adapt to few-shot cases without forgetting already trained domains.