Multi-Domain Dialogue Acts and Response Co-Generation

Abstract

Generating fluent and informative responses is of critical importance for task-oriented dialogue systems. Existing pipeline approaches generally predict multiple dialogue acts first and use them to assist response generation. There are at least two shortcomings with such approaches. First, the inherent structures of multi-domain dialogue acts are neglected. Second, the semantic associations between acts and responses are not taken into account for response generation. To address these issues, we propose a neural co-generation model that generates dialogue acts and responses concurrently. Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed. We train the two modules jointly using an uncertainty loss to adjust their task weights adaptively. Extensive experiments are conducted on the large-scale MultiWOZ dataset and the results show that our model achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.

arXiv commentTo appear at ACL 2020

References in corpus (8)

• A Deep Reinforced Model for Abstractive Summarization
• A Deep Reinforcement Learning Chatbot
• Modeling Coverage for Neural Machine Translation
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
• Global-Locally Self-Attentive Dialogue State Tracker
• Coverage Embedding Models for Neural Machine Translation
• A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts
• DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning

Cited by in corpus (2)

• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System
• Transferable Dialogue Systems and User Simulators