A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Understand

Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue.

• In an effort to model this kind of generative process, we propose a neural network-based generative architecture, with latent stochastic variables that span a variable number of time steps.
• We apply the proposed model to the task of dialogue response generation and compare it with recent neural network architectures.
• We evaluate the model performance through automatic evaluation metrics and by carrying out a human evaluation.