论文标题
通过知识库推理来改善实体歧义
Improving Entity Disambiguation by Reasoning over a Knowledge Base
论文作者
论文摘要
实体歧义（ED）的最新工作通常忽略了结构性知识库（KB）事实，而是依靠有限的KB信息子集，例如实体描述或类型。这限制了实体可以消除歧义的环境范围。为了允许使用所有KB事实以及描述和类型，我们介绍了一个ED模型，该模型通过以完全可区分的方式通过符号知识基础来链接实体。我们的模型平均超过了六个良好的ED数据集的最新基线。通过允许访问所有KB信息，我们的模型较少依赖于基于流行的实体先验，并提高了具有挑战性的Shadowlink数据集（强调不经常和模棱两可的实体）的性能，将其提高12.7 F1。
Recent work in entity disambiguation (ED) has typically neglected structured knowledge base (KB) facts, and instead relied on a limited subset of KB information, such as entity descriptions or types. This limits the range of contexts in which entities can be disambiguated. To allow the use of all KB facts, as well as descriptions and types, we introduce an ED model which links entities by reasoning over a symbolic knowledge base in a fully differentiable fashion. Our model surpasses state-of-the-art baselines on six well-established ED datasets by 1.3 F1 on average. By allowing access to all KB information, our model is less reliant on popularity-based entity priors, and improves performance on the challenging ShadowLink dataset (which emphasises infrequent and ambiguous entities) by 12.7 F1.
