Modeling Relation Paths for Knowledge Graph Completion

doi:10.1109/TKDE.2020.2970044

Modeling Relation Paths for Knowledge Graph Completion

2021-11-01

119

PRE

AI

DOI：10.1109/TKDE.2020.2970044

Original

Original request for help

Save

Abstract

En 中文

Knowledge graphs (KG) often encounter knowledge incompleteness. The path reasoning that predicts the unknown path relation between pairwise entities based on existing facts is one of the most promising approaches to the knowledge graph completion. However, most conventional path reasoning methods exclusively consider the entity description included in fact triples, ignoring both the type information of entities and the interaction between different semantic representations. In this study, we propose a novel method, Type-aware Attentive Path Reasoning (TAPR), to complete the knowledge graph by simultaneously considering KG structural information, textual information, and type information. More specifically, we first leverage types to enrich the representational learning of entities and relationships. Next, we describe a type-level attention to select the most relevant type of given entity in a specific triple without any predefined rules or patterns to reduce the impact of noisy types. After learning the distributed representation of all paths, path-level attention assigns different weights to paths, from which relations among entity pairs are calculated. We conduct a series of experiments on a real-world dataset to demonstrate the effectiveness of TAPR. Experimental results show that our method significantly outperforms all baselines on link prediction and entity prediction tasks.

Keywords:

Cognition

Semantics

Noise measurement

Data models

Data mining

Neural networks

Encyclopedias

Big data applications

semantic web

data mining

knowledge discovery

Modeling Relation Paths for Knowledge Graph Completion

Abstract

AI Summary

Journal

Organization