Biomedical Entity Linking with Triple-aware Pre-Training
Abstract: Compared to black-box neural networks, logic rules express explicit knowledge, can provide human-understandable explanations for reasoning processes, and have found their wide application in knowledge graphs and other downstream tasks. As extracting rules manually from large knowledge graphs is labour-intensive and often infeasible, automated rule learning has recently attracted significant interest, and a number of approaches to rule learning for knowledge graphs have been proposed. This survey aims to provide a review of approaches and a classification of state-of-the-art systems for learning first-order logic rules over knowledge graphs. A comparative analysis of various approaches to rule learning is conducted based on rule language biases, underlying methods, and evaluation metrics. The approaches we consider include inductive logic programming (ILP)-based, statistical path generalisation, and neuro-symbolic methods. Moreover, we highlight important and promising application scenarios of rule learning, such as rule-based knowledge graph completion, fact checking, and applications in other research areas.
Show BibTeX
@inproceedings{DBLP:conf/semtech4stld/YanMU25,
author = {Xi Yan and
Cedric M{\"{o}}ller and
Ricardo Usbeck},
editor = {Rima Dessi and
Jeenu Joy and
Danilo Dess{\`{\i}} and
Francesco Osborne and
Hidir Aras},
title = {Biomedical Entity Linking with Triple-aware Pre-Training},
booktitle = {Third International Workshop on Semantic Technologies and Deep Learning
Models for Scientific, Technical and Legal Data (SemTech4STLD 2025)
co-located with Extended Semantic Web Conference 2025 {(ESWC} 2025),
Portoroz, Slovenia, June 1st, 2025},
series = {{CEUR} Workshop Proceedings},
volume = {3979},
publisher = {CEUR-WS.org},
year = {2025},
url = {https://ceur-ws.org/Vol-3979/short2.pdf},
timestamp = {Thu, 11 Jun 2026 11:15:03 +0200},
biburl = {https://dblp.org/rec/conf/semtech4stld/YanMU25.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}