DKG: A Descriptive Knowledge Graph for Explaining Relationships between Entities

05/21/2022
by   Jie Huang, et al.
12

In this paper, we propose Descriptive Knowledge Graph (DKG) - an open and interpretable form of modeling relationships between entities. In DKGs, relationships between entities are represented by relation descriptions. For instance, the relationship between entities of machine learning and algorithm can be described as "Machine learning explores the study and construction of algorithms that can learn from and make predictions on data." To construct DKGs, we propose a self-supervised learning method to extract relation descriptions with the analysis of dependency patterns and a transformer-based relation description synthesizing model to generate relation descriptions. Experiments demonstrate that our system can extract and generate high-quality relation descriptions for explaining entity relationships.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset