DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialogue

TL;DR

DLGNet-Task is a unified, end-to-end neural network framework for multi-turn, multi-domain task-oriented dialogue that combines modular controllability with the efficiency of end-to-end training.

Contribution

It introduces a joint training approach for all dialogue system components using autoregressive transformers, improving efficiency and maintainability over traditional modular systems.

Findings

Achieves comparable performance to state-of-the-art on MultiWOZ2.1

Reduces development and maintenance effort for dialogue systems

Demonstrates effective joint training of all dialogue modules

Abstract

Task oriented dialogue (TOD) requires the complex interleaving of a number of individually controllable components with strong guarantees for explainability and verifiability. This has made it difficult to adopt the multi-turn multi-domain dialogue generation capabilities of streamlined end-to-end open-domain dialogue systems. In this paper, we present a new framework, DLGNet-Task, a unified task-oriented dialogue system which employs autoregressive transformer networks such as DLGNet and GPT-2/3 to complete user tasks in multi-turn multi-domain conversations. Our framework enjoys the controllable, verifiable, and explainable outputs of modular approaches, and the low development, deployment and maintenance cost of end-to-end systems. Treating open-domain system components as additional TOD system modules allows DLGNet-Task to learn the joint distribution of the inputs and outputs of all the functional blocks of existing modular approaches such as, natural language understanding (NLU), state tracking, action policy, as well as natural language generation (NLG). Rather than training the modules individually, as is common in real-world systems, we trained them jointly with appropriate module separations. When evaluated on the MultiWOZ2.1 dataset, DLGNet-Task shows comparable performance to the existing state-of-the-art approaches. Furthermore, using DLGNet-Task in conversational AI systems reduces the level of effort required for developing, deploying, and maintaining intelligent assistants at scale.