Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding

TL;DR

This paper introduces an adversarial training approach to develop cross-domain slot filling models in spoken language understanding, reducing data annotation costs and improving performance across multiple domains.

Contribution

It proposes a novel adversarial learning method to create shared representations for multi-domain SLU, enhancing generalization and reducing the need for extensive domain-specific data.

Findings

Adversarial training improves domain-general slot filling F1 scores.

Shared representations enable better performance with fewer domain-specific samples.

Joint training with domain-specific models further enhances slot filling accuracy.

Abstract

The goal of this paper is to learn cross-domain representations for slot filling task in spoken language understanding (SLU). Most of the recently published SLU models are domain-specific ones that work on individual task domains. Annotating data for each individual task domain is both financially costly and non-scalable. In this work, we propose an adversarial training method in learning common features and representations that can be shared across multiple domains. Model that produces such shared representations can be combined with models trained on individual domain SLU data to reduce the amount of training samples required for developing a new domain. In our experiments using data sets from multiple domains, we show that adversarial training helps in learning better domain-general SLU models, leading to improved slot filling F1 scores. We further show that applying adversarial learning on domain-general model also helps in achieving higher slot filling performance when the model is jointly optimized with domain-specific models.