Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

Abstract

Conversations have an intrinsic one-to-many property, which means that multiple responses can be appropriate for the same dialog context. In task-oriented dialogs, this property leads to different valid dialog policies towards task completion. However, none of the existing task-oriented dialog generation approaches takes this property into account. We propose a Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses. Specifically, we first use dialog states to summarize the dialog history, and then discover all possible mappings from every dialog state to its different valid system actions. During dialog system training, we enable the current dialog state to map to all valid system actions discovered in the previous process to create additional state-action pairs. By incorporating these additional pairs, the dialog policy learns a balanced action distribution, which further guides the dialog model to generate diverse responses. Experimental results show that the proposed framework consistently improves dialog policy diversity, and results in improved response diversity and appropriateness. Our model obtains state-of-the-art results on MultiWOZ.

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• The Curious Case of Neural Text Degeneration
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• Hierarchical Neural Story Generation
• ConvLab: Multi-Domain End-to-End Dialog System Platform
• Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
• Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability

Cited by in corpus (11)

• A Simple Language Model for Task-Oriented Dialogue
• SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System
• Robust Conversational AI with Grounded Text Generation
• MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
• Paraphrase Augmented Task-Oriented Dialog Generation
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems
• RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling
• A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining
• UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues
• Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming