We develop a generative attention-based approach to modeling structured entities comprising different property types, such as numerical, categorical, string, and composite. This approach handles such heterogeneous data through a mixed continuous-discrete diffusion process over the properties. Our flexible framework can model entities with arbitrary hierarchical properties, enabling applications to structured Knowledge Base (KB) entities and tabular data. Our approach obtains state-of-the-art performance on a majority of cases across 15 datasets. In addition, experiments with a device KB and a nuclear physics dataset demonstrate the model's ability to learn representations useful for entity completion in diverse settings. This has many downstream use cases, including modeling numerical properties with high accuracy - critical for science applications, which also benefit from the model's inherent probabilistic nature.

翻译：我们提出了一种基于生成式注意力机制的方法，用于建模包含数值、类别、字符串及复合类型等不同属性类型的结构化实体。该方法通过混合连续-离散扩散过程处理这些异质性属性。我们的灵活框架能够对具有任意层级属性的实体进行建模，使其可应用于结构化知识库实体及表格数据。在15个数据集的多数案例中，本方法取得了最先进的性能。此外，在设备知识库和核物理数据集上的实验表明，该模型能够学习到适用于不同场景中实体补全任务的表示。这催生了诸多下游应用场景，包括对科学应用至关重要且需高精度的数值属性建模——此类应用亦得益于模型固有的概率特性。