Combining Embeddings and Rules for Fact Prediction - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Combining Embeddings and Rules for Fact Prediction

Résumé

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.
Fichier principal
Vignette du fichier
aib-2022.pdf (824.11 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04462010 , version 1 (16-02-2024)

Identifiants

Citer

Armand Boschin, Nitisha Jain, Gurami Keretchashvili, Fabian M. Suchanek. Combining Embeddings and Rules for Fact Prediction. International Research School in Artificial Intelligence in Bergen, 2022, Bergen (NO), Norway. ⟨10.4230/OASIcs.AIB.2022.4⟩. ⟨hal-04462010⟩
17 Consultations
15 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More