2026-07-23T20:15:14Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:16002 2024-03-06T10:31:40Z ddc:004 open_access

Combining Embeddings and Rules for Fact Prediction (Invited Paper) Boschin, Armand Jain, Nitisha Keretchashvili, Gurami Suchanek, Fabian Rule Mining Embeddings Knowledge Bases Deep Learning Knowledge bases are typically incomplete, meaning that they are missing information that we would expect to be there. Recent years have seen two main approaches to guess missing facts: Rule Mining and Knowledge Graph Embeddings. The first approach is symbolic, and finds rules such as "If two people are married, they most likely live in the same city". These rules can then be used to predict missing statements. Knowledge Graph Embeddings, on the other hand, are trained to predict missing facts for a knowledge base by mapping entities to a vector space. Each of these approaches has their strengths and weaknesses, and this article provides a survey of neuro-symbolic works that combine embeddings and rule mining approaches for fact prediction. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Armand Boschin and Nitisha Jain and Gurami Keretchashvili and Fabian Suchanek 2022 Is Part Of OASIcs, Volume 99, International Research School in Artificial Intelligence in Bergen (AIB 2022) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.AIB.2022.4 urn:nbn:de:0030-drops-160021 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.AIB.2022.4 eng https://creativecommons.org/licenses/by/4.0/legalcode