主催: The Japanese Society for Artificial Intelligence
会議名: 第34回全国大会(2020)
回次: 34
開催地: Online
開催日: 2020/06/09 - 2020/06/12
Entity type information plays an important role in knowledge graphs (KGs). In a KG, an entity usually holds multiple type properties. In this paper, we address the entity type ranking problem by means of knowledge graph embedding models. We try to show how entity type ranking can exhibit the corresponding entity’s characteristics. In our work, we show that entity type ranking can be seen as a special case of the KG completion problem. Our proposed approach outperforms the state-of-the-art type ranking models while, at the same time, being more efficient and scalable.