Toward Continual Learning for Conversational Agents

Abstract

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the lack of modularity. Previous studies adopted a hybrid approach with knowledge-based components either to abstract out domain-specific information or to augment data to cover more diverse patterns. On the contrary, we propose to directly address the problem using recent developments in the space of continual learning for neural models. Specifically, we adopt a domain-independent neural conversational model and introduce a novel neural continual learning algorithm that allows a conversational agent to accumulate skills across different tasks in a data-efficient way. To the best of our knowledge, this is the first work that applies continual learning to conversation systems. We verified the efficacy of our method through a conversational skill transfer from either synthetic dialogs or human-human dialogs to human-computer conversations in a customer support domain.

References in corpus (10)

• Overcoming catastrophic forgetting in neural networks
• A Neural Conversational Model
• Continual Learning Through Synaptic Intelligence
• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Less-forgetting Learning in Deep Neural Networks
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Learning End-to-End Goal-Oriented Dialog

Cited by in corpus (12)

• LAMOL: LAnguage MOdeling for Lifelong Language Learning
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
• Defining Benchmarks for Continual Few-Shot Learning
• Continual Learning in Recurrent Neural Networks
• Continual Learning for Sentence Representations Using Conceptors
• The Rapidly Changing Landscape of Conversational Agents
• Update Frequently, Update Fast: Retraining Semantic Parsing Systems in a Fraction of Time
• Lifelong Language Knowledge Distillation
• Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
• Continual Learning in Task-Oriented Dialogue Systems
• Data-Efficient Methods for Dialogue Systems
• Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout