DEER: Descriptive Knowledge Graph for Explaining Entity Relationships

TL;DR

DEER introduces a self-supervised approach to create an open, descriptive knowledge graph by generating free-text relation descriptions, eliminating the need for human annotation.

Contribution

The paper presents a novel self-supervised method for extracting and synthesizing relation descriptions to build an informative knowledge graph.

Findings

High-quality relation descriptions are effectively extracted and generated.

The system operates without human-labeled data.

DEER enables open and descriptive knowledge graph construction.

Abstract

We propose DEER (Descriptive Knowledge Graph for Explaining Entity Relationships) - an open and informative form of modeling entity relationships. In DEER, relationships between entities are represented by free-text relation descriptions. For instance, the relationship between entities of machine learning and algorithm can be represented as ``Machine learning explores the study and construction of algorithms that can learn from and make predictions on data.'' To construct DEER, we propose a self-supervised learning method to extract relation descriptions with the analysis of dependency patterns and generate relation descriptions with a transformer-based relation description synthesizing model, where no human labeling is required. Experiments demonstrate that our system can extract and generate high-quality relation descriptions for explaining entity relationships. The results suggest that we can build an open and informative knowledge graph without human annotation.