Many current web pages include structured data which can directly be processed and used. Search engines, in particular, gather that structured data and provide question answering capabilities over the integrated data with an entity-centric presentation of the results. Due to the decentralized nature of the web, multiple structured data sources can provide similar information about an entity. But data from different sources may involve different vocabularies and modeling granularities, which makes integration difficult. We present FusE, an approach that identifies similar entity-specific data across sources, independent of the vocabulary and data modeling choices. We apply our method along the scenario of a trustable knowledge panel, conduct experiments in which we identify and process entity data from web sources, and compare the output to a competing system. The results underline the advantages of the presented entity-centric data fusion approach.

中文翻译：

---

保险丝

当前许多网页都包含可以直接处理和使用的结构化数据。尤其是搜索引擎，它收集结构化数据，并通过以实体为中心的结果呈现方式为集成数据提供问答功能。由于网络的分散性，多个结构化数据源可以提供有关实体的类似信息。但是来自不同来源的数据可能涉及不同的词汇和建模粒度，这使得集成变得困难。我们提出了 FusE，这是一种跨源识别类似实体特定数据的方法，独立于词汇表和数据建模选择。我们将我们的方法应用于可信知识面板的场景，进行实验，在这些实验中我们识别和处理来自网络资源的实体数据，并将输出与竞争系统进行比较。结果强调了所提出的以实体为中心的数据融合方法的优势。