Natural language generation from structured data mainly focuses on surface-level descriptions, suffering from uncontrollable content selection and low fidelity. Previous works leverage logical forms to facilitate logical knowledge-conditioned text generation. Though achieving remarkable progress, they are data-hungry, which makes the adoption for real-world applications challenging with limited data. To this end, this paper proposes a unified framework for logical knowledge-conditioned text generation in the few-shot setting. With only a few seeds logical forms (e.g., 20/100 shot), our approach leverages self-training and samples pseudo logical forms based on content and structure consistency. Experimental results demonstrate that our approach can obtain better few-shot performance than baselines.
翻译:从结构化数据中产生自然语言,主要侧重于地表层次的描述,受到无法控制的内容选择和低忠诚度的影响。以前的作品利用逻辑形式便利了逻辑知识条件的文本生成。虽然取得了显著进展,但它们是数据饥饿,因此采用现实世界应用程序时使用的数据有限。为此,本文件提议了一个统一框架,用于在短片环境中以逻辑知识方式生成文本。只有少数种子的逻辑形式(如20/100射击),我们的方法根据内容和结构的一致性,利用自我培训和样本模拟假的逻辑形式。实验结果表明,我们的方法可以比基线取得更好的少见性能。