no code implementations • 31 Jul 2023 • Mehwish Alam, Frank van Harmelen, Maribel Acosta
Most of the current algorithms consider a KG as a multidirectional labeled graph and lack the ability to capture the semantics underlying the schematic information.
1 code implementation • 10 Jun 2022 • Alessandro Daniele, Emile van Krieken, Luciano Serafini, Frank van Harmelen
Using a new algorithm called Iterative Local Refinement (ILR), we combine refinement functions to find refined predictions for logical formulas of any complexity.
no code implementations • 23 Feb 2021 • Michael van Bekkum, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, Annette ten Teije
In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems.
no code implementations • 4 Jun 2020 • Emile van Krieken, Erman Acar, Frank van Harmelen
In this paper, we investigate how implications from the fuzzy logic literature behave in a differentiable setting.
1 code implementation • 14 Feb 2020 • Emile van Krieken, Erman Acar, Frank van Harmelen
Finally, we empirically show that it is possible to use Differentiable Fuzzy Logics for semi-supervised learning, and compare how different operators behave in practice.
1 code implementation • 13 Aug 2019 • Emile van Krieken, Erman Acar, Frank van Harmelen
We introduce Differentiable Reasoning (DR), a novel semi-supervised learning technique which uses relational background knowledge to benefit from unlabeled data.
no code implementations • 1 Aug 2019 • Floris den Hengst, Mark Hoogendoorn, Frank van Harmelen, Joost Bosman
Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e. g. take the personal context of users into account.
no code implementations • 24 Jul 2019 • Joe Raad, Nathalie Pernelle, Fatiha Saïs, Wouter Beek, Frank van Harmelen
In a decentralised knowledge representation system such as the Web of Data, it is common and indeed desirable for different knowledge graphs to overlap.
no code implementations • 19 Jun 2019 • Luigi Asprino, Wouter Beek, Paolo Ciancarini, Frank van Harmelen, Valentina Presutti
This paper presents an empirical study aiming at understanding the modeling style and the overall semantic structure of Linked Open Data.
no code implementations • 29 May 2019 • Frank van Harmelen, Annette ten Teije
We propose a set of compositional design patterns to describe a large variety of systems that combine statistical techniques from machine learning with symbolic techniques from knowledge representation.