arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.07938cs.LGcs.AIcs.CLstat.ML
收藏

知识图谱中的类型增广关系预测

Type-augmented Relation Prediction in Knowledge Graphs

Rensselaer Polytechnic Institute(伦斯勒理工学院);IBM Research(IBM研究院)

Zijun Cui, Pavan Kapanipathi, Kartik Talamadupula, Tian Gao, Qiang Ji

摘要:

知识图谱(KGs)对于许多现实世界的应用是非常重要的,但是它们通常遭受以实体之间的缺失关系的形式的不完整信息。知识图谱补全(也称为关系预测)是在现有事实的情况下推断缺失事实的任务。大多数现有的工作是通过最大限度地提高所观察到的实例级三元组的可能性。然而,没有太多的关注,支付的本体信息,如类型信息的实体和关系。在这项工作中,我们提出了一个类型增强的关系预测(TaRP)的方法,在那里我们同时适用于类型信息和实例级信息的关系预测。特别地,将类型信息和实例级信息分别编码为先验概率和关系似然,并按照贝叶斯规则进行组合。我们提出的TaRP方法在四个基准数据集上实现了比最先进方法更好的性能:FB 15 K,FB 15 K-237,YAGO 26 K-906和DB 111 K-174。此外,我们表明,TaRP实现了显着提高数据效率。更重要的是,从一个特定的数据集提取的类型信息可以很好地推广到其他数据集通过所提出的TaRP模型。

英文摘要:

Knowledge graphs (KGs) are of great importance to many real world applications, but they generally suffer from incomplete information in the form of missing relations between entities. Knowledge graph completion (also known as relation prediction) is the task of inferring missing facts given existing ones. Most of the existing work is proposed by maximizing the likelihood of observed instance-level triples. Not much attention, however, is paid to the ontological information, such as type information of entities and relations. In this work, we propose a type-augmented relation prediction (TaRP) method, where we apply both the type information and instance-level information for relation prediction. In particular, type information and instance-level information are encoded as prior probabilities and likelihoods of relations respectively, and are combined by following Bayes' rule. Our proposed TaRP method achieves significantly better performance than state-of-the-art methods on four benchmark datasets: FB15K, FB15K-237, YAGO26K-906, and DB111K-174. In addition, we show that TaRP achieves significantly improved data efficiency. More importantly, the type information extracted from a specific dataset can generalize well to other datasets through the proposed TaRP model.

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。

↑