[1O4-GS-4] Knowledge utilization and sharing: Semantic web (1)

[1O4-GS-4-03] A Model for Traversing and Scoring Path Queries in Knowledge Graphs

〇Kenta Hama¹, Takashi Matsubara¹, Kuniaki Uehara¹ (1. Kobe University)

Keywords:Knowledge Base, Link Prediction, Knowledge Graph Embedding

A knowledge graph is represented by a set of two entities and the relations,
and used for various tasks such as information extraction, question answering, and sentence understanding.
Since many knowledge graphs include missing relations, Knowledge Graph Completion (KGC) is important.
Translation-based model can predict them by learning transition functions and embeddings of entities.
However, many of these models are known that the accuracy of prediction is reduced in tasks
such as Path Query Answering (PQA), which makes multiple transitions.
On the other hand, if the transition embedding point is matched with the correct embedding point
in order to prevent the loss of prediction accuracy,
the embedding point having a one-to-many relationship will be collapsed into one point.
In this study, we tried to solve this problem by defining transition and evaluation functions separately in translation-based model.
The proposed method improved accuracy in PQA and KGC.