Domain Adaptation in Dialogue Systems using Transfer and Meta-Learning

TL;DR

This paper introduces DATML, a novel method combining transfer and meta-learning to enhance dialogue systems' ability to adapt to unseen domains with minimal data, outperforming previous models on MultiWOZ.

Contribution

The paper presents DATML, a new approach that integrates meta-learning with transfer learning to improve domain adaptation in dialogue systems, building upon and surpassing DiKTNet.

Findings

DATML outperforms DiKTNet on MultiWOZ in BLEU scores.

DATML achieves higher Entity F1 scores with limited data.

Meta-learning with Reptile enhances domain adaptation in dialogue models.

Abstract

Current generative-based dialogue systems are data-hungry and fail to adapt to new unseen domains when only a small amount of target data is available. Additionally, in real-world applications, most domains are underrepresented, so there is a need to create a system capable of generalizing to these domains using minimal data. In this paper, we propose a method that adapts to unseen domains by combining both transfer and meta-learning (DATML). DATML improves the previous state-of-the-art dialogue model, DiKTNet, by introducing a different learning technique: meta-learning. We use Reptile, a first-order optimization-based meta-learning algorithm as our improved training method. We evaluated our model on the MultiWOZ dataset and outperformed DiKTNet in both BLEU and Entity F1 scores when the same amount of data is available.