Capsule Networks for Low Resource Spoken Language Understanding

TL;DR

This paper explores the use of capsule networks to improve low-resource spoken language understanding, demonstrating superior performance over existing methods in various command-and-control applications with limited training data.

Contribution

It introduces a capsule network-based approach that effectively utilizes minimal training data for spoken language understanding without prior data collection.

Findings

Capsule networks outperform NMF and recent deep learning models in low-resource settings.

The proposed model achieves higher accuracy in three command-and-control tasks.

Capsule networks enable flexible, user-trained spoken language understanding systems.

Abstract

Designing a spoken language understanding system for command-and-control applications can be challenging because of a wide variety of domains and users or because of a lack of training data. In this paper we discuss a system that learns from scratch from user demonstrations. This method has the advantage that the same system can be used for many domains and users without modifications and that no training data is required prior to deployment. The user is required to train the system, so for a user friendly experience it is crucial to minimize the required amount of data. In this paper we investigate whether a capsule network can make efficient use of the limited amount of available training data. We compare the proposed model to an approach based on Non-negative Matrix Factorisation which is the state-of-the-art in this setting and another deep learning approach that was recently introduced for end-to-end spoken language understanding. We show that the proposed model outperforms the baseline models for three command-and-control applications: controlling a small robot, a vocally guided card game and a home automation task.