.png){kind=icon}
返回
Incorporating logic rules with textual representations for interpretable knowledge graph reasoning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2023.110787.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reasoning on knowledge graphs (KGs) is significant for downstream applications, such as question answering and information extraction. On the basis of using factual triples in KGs, learning logic rules has been explored to handle KG reasoning in an interpretable pattern. Some rule learning methods simply apply thresholds to reduce the exponential complexity caused by the vast candidate rules derived from KGs. Others are designed to prune candidates on the basis of embedding facts in the KG. However, these methods only consider the factual triples, which mainly contain structural information, and ignore sufficient semantic information in real-world KGs. This situation weakens the methods in searching for high-quality rules. To this end, we propose a joint method by incorporating logic rules with textual representations for interpretable KG reasoning, named LoTus. Firstly, LoTus obtains the structural embeddings with only factual triples, and the textual embeddings with descriptions of entities, which are later integrated into the representations of entities and relations. Secondly, top candidate rules are selected by a proposed joint pruning strategy incorporating structural and textual representations in KGs. Finally, LoTus captures high-quality rules and removes low-quality ones by a filtering process with metrics of rules. It reduces the time complexity on KG reasoning by learning rules and provides interpretability simultaneously. Extensive experiments on different datasets show that LoTus obtains competitive performance comparing to baselines on KG reasoning metrics Hits@1, Hits@10 and mean reciprocal rank (MRR), and achieves significant superiority among the recent rule learning methods.& COPY; 2023 Elsevier B.V. All rights reserved.
Keyword:
Knowledge graph reasoning
First-order horn rules
Interpretable reasoning
Rule learning
期刊
K
IF:
7.6
论文数:
1.2W
被引数:
4.5W
机构
引用论文
Kinematic analysis of limb movements in neuropsychological research: Subtle deficits and recovery of function.神经心理学研究中肢体运动的运动学分析: 细微的缺陷和功能的恢复。
PREAI
分享收藏Exceptionally preserved soft parts in fossils from the Lower Ordovician of Morocco clarify stylophoran affinities within basal deuterostomes.png)
Geobios
OAAI
GeobiosIF0
OAAI分享收藏Distantly supervised relation extraction with KB-enhanced reconstructed latent iterative graph networks基于KB增强的重构潜在迭代图网络的远距离监督关系提取
PREAI
分享收藏Impact of Age at Administration, Lysosomal Storage, and Transgene Regulatory Elements on AAV2/8-Mediated Rat Liver TransductionPLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏分享收藏分享收藏
查看更多内容