Rule-Guided Joint Embedding Learning over Knowledge Graphs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Qisong, Lin, Ji, Wei, Sijia, Liu, Neng
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918133073182720
author Li, Qisong
Lin, Ji
Wei, Sijia
Liu, Neng
author_facet Li, Qisong
Lin, Ji
Wei, Sijia
Liu, Neng
contents Recent studies on knowledge graph embedding focus on mapping entities and relations into low-dimensional vector spaces. While most existing models primarily exploit structural information, knowledge graphs also contain rich contextual and textual information that can enhance embedding effectiveness. In this work, we propose a novel model that integrates both contextual and textual signals into entity and relation embeddings through a graph convolutional network. To better utilize context, we introduce two metrics: confidence, computed via a rule-based method, and relatedness, derived from textual representations. These metrics enable more precise weighting of contextual information during embedding learning. Extensive experiments on two widely used benchmark datasets demonstrate the effectiveness of our approach, showing consistent improvements over strong baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02968
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Rule-Guided Joint Embedding Learning over Knowledge Graphs
Li, Qisong
Lin, Ji
Wei, Sijia
Liu, Neng
Computation and Language
Recent studies on knowledge graph embedding focus on mapping entities and relations into low-dimensional vector spaces. While most existing models primarily exploit structural information, knowledge graphs also contain rich contextual and textual information that can enhance embedding effectiveness. In this work, we propose a novel model that integrates both contextual and textual signals into entity and relation embeddings through a graph convolutional network. To better utilize context, we introduce two metrics: confidence, computed via a rule-based method, and relatedness, derived from textual representations. These metrics enable more precise weighting of contextual information during embedding learning. Extensive experiments on two widely used benchmark datasets demonstrate the effectiveness of our approach, showing consistent improvements over strong baselines.
title Rule-Guided Joint Embedding Learning over Knowledge Graphs
topic Computation and Language
url https://arxiv.org/abs/2401.02968