Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines
This work is significant for researchers and developers working on task-oriented dialogue systems, offering a way to understand and potentially debug neural NLG models, which are typically black boxes.
This paper addresses the lack of interpretability in end-to-end neural networks for natural language generation (NLG) in task-oriented dialogue systems. They propose a framework called Heterogeneous Rendering Machines (HRM) which achieves competitive performance with state-of-the-art methods on 5 benchmark datasets while providing interpretability.
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.