A Context-aware Natural Language Generator for Dialogue Systems

Abstract

We present a novel natural language generation system for spoken dialogue systems capable of entraining (adapting) to users' way of speaking, providing contextually appropriate responses. The generator is based on recurrent neural networks and the sequence-to-sequence approach. It is fully trainable from data which include preceding context along with responses to be generated. We show that the context-aware generator yields significant improvements over the baseline in both automatic metrics and a human pairwise preference test.

Accepted as a short paper for SIGDIAL 2016

References in corpus (2)

• Sequence to Sequence Learning with Neural Networks
• A Network-based End-to-End Trainable Task-oriented Dialogue System

Cited by in corpus (8)

• A Survey on Dialogue Systems: Recent Advances and New Frontiers
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• Why We Need New Evaluation Metrics for NLG
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts
• Modeling Intent, Dialog Policies and Response Adaptation for Goal-Oriented Interactions
• Show, Price and Negotiate: A Negotiator with Online Value Look-Ahead
• Neural MultiVoice Models for Expressing Novel Personalities in Dialog