Generative Deep Neural Networks for Dialogue: A Short Review

TL;DR

This paper reviews recent advances in generative deep neural network models for dialogue systems, emphasizing their ability to incorporate context, model uncertainty, and produce diverse, structured responses.

Contribution

It provides a comprehensive overview of recent generative encoder-decoder models for dialogue, highlighting their capabilities and challenges in natural language response generation.

Findings

Models better incorporate long-term dialogue history

Models effectively handle uncertainty and ambiguity

Models generate responses with high-level structural complexity

Abstract

Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising results for unstructured tasks, such as word-level dialogue response generation. The hope is that such models will be able to leverage massive amounts of data to learn meaningful natural language representations and response generation strategies, while requiring a minimum amount of domain knowledge and hand-crafting. An important challenge is to develop models that can effectively incorporate dialogue context and generate meaningful and diverse responses. In support of this goal, we review recently proposed models based on generative encoder-decoder neural network architectures, and show that these models have better ability to incorporate long-term dialogue history, to model uncertainty and ambiguity in dialogue, and to generate responses with high-level compositional structure.