SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System

TL;DR

This paper introduces SUMBT+LaRL, a multi-domain end-to-end neural dialog system that combines two models with a three-step training process, achieving state-of-the-art success rates in task-oriented dialog benchmarks.

Contribution

The paper presents a novel modularized end-to-end multi-domain dialog system that integrates SUMBT+ and LaRL models with a three-step training framework, including reinforcement learning.

Findings

Achieved 85.4% success rate on corpus-based evaluation.

Achieved 81.40% success rate on DSTC8 simulator evaluation.

First comprehensive study of a modularized E2E multi-domain dialog system.

Abstract

The recent advent of neural approaches for developing each dialog component in task-oriented dialog systems has remarkably improved, yet optimizing the overall system performance remains a challenge. Besides, previous research on modeling complicated multi-domain goal-oriented dialogs in end-to-end fashion has been limited. In this paper, we present an effective multi-domain end-to-end trainable neural dialog system SUMBT+LaRL that incorporates two previous strong models and facilitates them to be fully differentiable. Specifically, the SUMBT+ estimates user-acts as well as dialog belief states, and the LaRL models latent system action spaces and generates responses given the estimated contexts. We emphasize that the training framework of three steps significantly and stably increase dialog success rates: separately pretraining the SUMBT+ and LaRL, fine-tuning the entire system, and then reinforcement learning of dialog policy. We also introduce new reward criteria of reinforcement learning for dialog policy training. Then, we discuss experimental results depending on the reward criteria and different dialog evaluation methods. Consequently, our model achieved the new state-of-the-art success rate of 85.4% on corpus-based evaluation, and a comparable success rate of 81.40% on simulator-based evaluation provided by the DSTC8 challenge. To our best knowledge, our work is the first comprehensive study of a modularized E2E multi-domain dialog system that learning from each component to the entire dialog policy for task success.