Learning Interpretable Latent Dialogue Actions With Less Supervision

TL;DR

This paper introduces a variational recurrent neural network architecture for task-oriented dialogues that learns interpretable latent dialogue actions with minimal supervision, outperforming previous models in perplexity and BLEU scores.

Contribution

It presents a novel VRNN-based model that models system and user turns separately, enabling explainable latent dialogue actions without explicit semantic annotations.

Findings

Outperforms previous models in perplexity and BLEU scores

Models system and user turns separately for better interpretability

Proposes a new method to measure dialogue success without expert annotations

Abstract

We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit annotation of semantic information. Unlike previous works, our approach models the system and user turns separately and performs database query modeling, which makes the model applicable to task-oriented dialogues while producing easily interpretable action latent variables. We show that our model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets, and we propose a way to measure dialogue success without the need for expert annotation. Finally, we propose a novel way to explain semantics of the latent variables with respect to system actions.