End-to-End Task-Completion Neural Dialogue Systems

TL;DR

This paper introduces an end-to-end neural dialogue system for task completion that directly interacts with databases, improving robustness and performance over traditional modular systems, especially in noisy environments.

Contribution

It proposes a novel end-to-end learning framework with reinforcement learning for dialogue management, enhancing robustness and performance in task-oriented dialogue systems.

Findings

Outperforms modularized systems in objective and subjective evaluations

Demonstrates robustness to language understanding errors

Effective in a movie-ticket booking domain

Abstract

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance of the entire system is not robust to the accumulated errors. This paper presents a novel end-to-end learning framework for task-completion dialogue systems to tackle such issues. Our neural dialogue system can directly interact with a structured database to assist users in accessing information and accomplishing certain tasks. The reinforcement learning based dialogue manager offers robust capabilities to handle noises caused by other components of the dialogue system. Our experiments in a movie-ticket booking domain show that our end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.