We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data. Our proposed method aims to improve performance in multi-task training, zero-shot and few-shot scenarios by providing a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations. We demonstrate that our proposed approach can effectively adapt to new structured forms, and can improve performance in comparison to current methods. For example, our method resulted in a 66% improvement in zero-shot BLEU scores when transferring models trained on table inputs to a knowledge graph dataset. Our proposed method is an important step towards a more general data-to-text generation framework.

翻译：我们提出了一种新颖的结构化数据到文本生成方法，旨在解决现有方法主要局限于特定类型结构化数据的不足。通过提供一种能够处理表格、知识图谱三元组、语义表示等多种结构化数据形式的统一表示，所提方法致力于提升多任务训练、零样本及小样本场景下的性能。实验表明，该方法能有效适应新的结构化形式，并在性能上优于现有方法。例如，当将基于表格输入训练的模型迁移至知识图谱数据集时，我们的方法在零样本BLEU分数上实现了66%的提升。本研究是迈向更通用的数据到文本生成框架的重要一步。