新的嵌入式传递关系表示与求值协议
New Embedded Representations and Evaluation Protocols for Inferring Transitive Relations
摘要:
除了词嵌入之外,知识图谱(KG)组件(诸如实体、类型和关系)的连续表示被广泛用于实体提及消歧、关系推理和深度问答。在使用高斯、全息和复杂嵌入对一般、非对称或反对称KG关系进行建模方面已经取得了很大的进展。这些都没有直接强制is-instance-of和is-subtype-of关系中固有的传递性。最近的一个建议,称为顺序嵌入(OE),要求表示子类型的向量在元素上优于表示超类型的向量。然而,断言和评估这些约束的方式具有一些限制。在这篇简短的研究笔记中,我们对表示和推断传递关系做出了三个贡献。首先,我们提出并证明了对OE损失目标的重大改进。第二,我们提出了一个新的表示类型的超矩形区域,推广和改进OE。第三,我们表明,目前的一些协议,以评估传递关系推理可能是误导,并提供了一个健全的替代方案。我们没有使用现成的黑盒深度学习模块,而是使用基本的几何考虑来开发我们的训练网络。
英文摘要:
Beyond word embeddings, continuous representations of knowledge graph (KG) components, such as entities, types and relations, are widely used for entity mention disambiguation, relation inference and deep question answering. Great strides have been made in modeling general, asymmetric or antisymmetric KG relations using Gaussian, holographic, and complex embeddings. None of these directly enforce transitivity inherent in the is-instance-of and is-subtype-of relations. A recent proposal, called order embedding (OE), demands that the vector representing a subtype elementwise dominates the vector representing a supertype. However, the manner in which such constraints are asserted and evaluated have some limitations. In this short research note, we make three contributions specific to representing and inferring transitive relations. First, we propose and justify a significant improvement to the OE loss objective. Second, we propose a new representation of types as hyper-rectangular regions, that generalize and improve on OE. Third, we show that some current protocols to evaluate transitive relation inference can be misleading, and offer a sound alternative. Rather than use black-box deep learning modules off-the-shelf, we develop our training networks using elementary geometric considerations.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。