Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines

TL;DR

This paper introduces heterogeneous rendering machines (HRM), a novel framework that enhances interpretability in neural natural language generation for task-oriented dialogue systems by explicitly modeling rendering processes.

Contribution

The paper proposes HRM, a new interpretable framework with multiple decoders and a mode switcher, improving understanding of neural NLG in dialogue systems.

Findings

HRM achieves competitive BLEU scores on benchmark datasets.

Qualitative analysis demonstrates HRM's interpretability.

Human evaluation confirms the model's explainability.

Abstract

End-to-end neural networks have achieved promising performances in natural language generation (NLG). However, they are treated as black boxes and lack interpretability. To address this problem, we propose a novel framework, heterogeneous rendering machines (HRM), that interprets how neural generators render an input dialogue act (DA) into an utterance. HRM consists of a renderer set and a mode switcher. The renderer set contains multiple decoders that vary in both structure and functionality. For every generation step, the mode switcher selects an appropriate decoder from the renderer set to generate an item (a word or a phrase). To verify the effectiveness of our method, we have conducted extensive experiments on 5 benchmark datasets. In terms of automatic metrics (e.g., BLEU), our model is competitive with the current state-of-the-art method. The qualitative analysis shows that our model can interpret the rendering process of neural generators well. Human evaluation also confirms the interpretability of our proposed approach.