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. The experiments demonstrate that our model improves upon recently proposed models and that the latent variables facilitate the generation of long outputs and maintain the context.
@article{arxiv.1605.06069,
title = {A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues},
author = {Iulian Vlad Serban and Alessandro Sordoni and Ryan Lowe and Laurent Charlin and Joelle Pineau and Aaron Courville and Yoshua Bengio},
journal= {arXiv preprint arXiv:1605.06069},
year = {2016}
}