Consistency of a model -- that is, the invariance of its behavior under meaning-preserving alternations in its input -- is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge? To this end, we create ParaRel, a high-quality resource of cloze-style query English paraphrases. It contains a total of 328 paraphrases for 38 relations. Using ParaRel, we show that the consistency of all PLMs we experiment with is poor -- though with high variance between relations. Our analysis of the representational spaces of PLMs suggests that they have a poor structure and are currently not suitable for representing knowledge robustly. Finally, we propose a method for improving model consistency and experimentally demonstrate its effectiveness.

翻译：一种模式的一致性 -- -- 即在输入中根据保留含义的交替而改变其行为 -- -- 在自然语言处理中是一种非常可取的特性。在本文中,我们研究的问题是:在事实知识方面,预先掌握的语言模式是否与事实知识一致?为此目的,我们创建了ParaRel,这是凝聚式问答英语句的高质量资源,共包含38个关系的328个参数。我们使用Pararel 表明,我们试验的所有PLM的一致性都很差 -- -- 尽管在关系上差异很大。我们对PLM的代表空间的分析表明,它们的结构很差,目前不适合强有力地代表知识。最后,我们提出了改进模式一致性和实验性地展示其有效性的方法。