Entity Relatedness Test Dataset

The entity relatedness problem refers to the question of computing the relationship paths that better describe the connectivity between a given entity pair. This dataset supports the evaluation of approaches that address the entity relatedness problem. It covers two familiar domains, music and movies, and uses data available in IMDb and last.fm, which are popular reference datasets in these domains. The dataset contains 20 entity pairs from each of these domains and, for each entity pair, a ranked list with 50 relationship paths. It also contains entity ratings and property relevance scores for the entities and properties used in the paths.实体关联度问题（entity relatedness problem）指的是求解能够更精准刻画给定实体对之间连通关系的路径的一类问题。本数据集可用于支撑针对该问题的各类求解方法的评估工作。该数据集覆盖音乐与电影两大主流领域，采用了两类领域内广受欢迎的参考数据集IMDb与last.fm中的公开数据。每个领域均包含20组实体对，且针对每组实体对，提供一份包含50条关系路径的排序列表。此外，数据集还收录了路径所涉及实体的实体评分，以及路径中使用的属性对应的属性关联度得分。