Connecting Embeddings for Knowledge Graph Entity Typing

Yu Zhao, anxiang zhang, Ruobing Xie, Kang Liu, Xiaojie WANG

Abstract Paper Share

Information Extraction Long Paper

Session 11B: Jul 8 (06:00-07:00 GMT)
Session 12B: Jul 8 (09:00-10:00 GMT)
Abstract: Knowledge graph (KG) entity typing aims at inferring possible missing entity type instances in KG, which is a very significant but still under-explored subtask of knowledge graph completion. In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge in KGs. Specifically, we present two distinct knowledge-driven effective mechanisms of entity type inference. Accordingly, we build two novel embedding models to realize the mechanisms. Afterward, a joint model via connecting them is used to infer missing entity type instances, which favors inferences that agree with both entity type instances and triple knowledge in KGs. Experimental results on two real-world datasets (Freebase and YAGO) demonstrate the effectiveness of our proposed mechanisms and models for improving KG entity typing. The source code and data of this paper can be obtained from: https://github.com/Adam1679/ConnectE .
You can open the pre-recorded video in a separate window.
NOTE: The SlidesLive video may display a random order of the authors. The correct author list is shown at the top of this webpage.

Similar Papers