Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems

TL;DR

This paper systematically studies how language understanding errors affect reinforcement learning-based dialogue systems, revealing that slot errors are more impactful and that RL systems can learn effective confirmation strategies to improve robustness.

Contribution

It provides empirical insights into the impact of different language understanding errors and demonstrates the ability of RL dialogue systems to learn confirmation strategies for better performance.

Findings

Slot-level errors significantly affect system performance

RL systems can learn when and what to confirm

Confirmation strategies improve robustness

Abstract

Language understanding is a key component in a spoken dialogue system. In this paper, we investigate how the language understanding module influences the dialogue system performance by conducting a series of systematic experiments on a task-oriented neural dialogue system in a reinforcement learning based setting. The empirical study shows that among different types of language understanding errors, slot-level errors can have more impact on the overall performance of a dialogue system compared to intent-level errors. In addition, our experiments demonstrate that the reinforcement learning based dialogue system is able to learn when and what to confirm in order to achieve better performance and greater robustness.