Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data

Abstract

Natural language generation plays a critical role in spoken dialogue systems. We present a new approach to natural language generation for task-oriented dialogue using recurrent neural networks in an encoder-decoder framework. In contrast to previous work, our model uses both lexicalized and delexicalized components i.e. slot-value pairs for dialogue acts, with slots and corresponding values aligned together. This allows our model to learn from all available data including the slot-value pairing, rather than being restricted to delexicalized slots. We show that this helps our model generate more natural sentences with better grammar. We further improve our model's performance by transferring weights learnt from a pretrained sentence auto-encoder. Human evaluation of our best-performing model indicates that it generates sentences which users find more appealing.

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Recurrent Neural Network Regularization
• A Neural Conversational Model
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking

Cited by in corpus (4)

• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• Why We Need New Evaluation Metrics for NLG
• Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention