Plan-then-Generate: Controlled Data-to-Text Generation via Planning
This addresses the need for better controllability in data-to-text models for real-world applications, representing a novel method for a known bottleneck.
The paper tackles the problem of controlling structure in neural data-to-text generation by proposing a Plan-then-Generate framework, which improves generation quality and output diversity on benchmark datasets like ToTTo and WebNLG.
Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In this study, we propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-to-text models. Extensive experiments and analyses are conducted on two benchmark datasets, ToTTo and WebNLG. The results show that our model is able to control both the intra-sentence and inter-sentence structure of the generated output. Furthermore, empirical comparisons against previous state-of-the-art methods show that our model improves the generation quality as well as the output diversity as judged by human and automatic evaluations.