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

arXiv: https://arxiv.org/abs/2012.14645 · HTML: https://mlsanity.com/paper/2012.14645/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2020.

## Built on by (most cited first, 2 of 2)

- [Explicit Syntactic Guidance for Neural Text Generation](https://mlsanity.com/paper/2306.11485/) (2023)
- [Neural Sequence Segmentation as Determining the Leftmost Segments](https://mlsanity.com/paper/2104.07217/) (2021)

## Abstract (arXiv)

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.