Large language models and knowledge graphs: Opportunities and challenges
Large Language Models (LLMs) have taken Knowledge Representation--and the world--by
storm. This inflection point marks a shift from explicit knowledge representation to a renewed …
storm. This inflection point marks a shift from explicit knowledge representation to a renewed …
Olala: Ontology matching with large language models
S Hertling, H Paulheim - Proceedings of the 12th Knowledge Capture …, 2023 - dl.acm.org
Ontology (and more generally: Knowledge Graph) Matching is a challenging task where
information in natural language is one of the most important signals to process. With the rise …
information in natural language is one of the most important signals to process. With the rise …
Efficient Axiomatization of OWL 2 EL Ontologies from Data by Means of Formal Concept Analysis
F Kriegel - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
We present an FCA-based axiomatization method that produces a complete OWL 2 EL TBox
(the terminological part of an OWL 2 EL ontology) from a graph dataset in at most …
(the terminological part of an OWL 2 EL ontology) from a graph dataset in at most …
Taxonomy completion via implicit concept insertion
\beginabstract High quality taxonomies play a critical role in various domains such as e-
commerce, web search and ontology engineering. While there has been extensive work on …
commerce, web search and ontology engineering. While there has been extensive work on …
Using Large Language Models for OntoClean-based Ontology Refinement
Y Zhao, N Vetter, K Aryan - arXiv preprint arXiv:2403.15864, 2024 - arxiv.org
This paper explores the integration of Large Language Models (LLMs) such as GPT-3.5 and
GPT-4 into the ontology refinement process, specifically focusing on the OntoClean …
GPT-4 into the ontology refinement process, specifically focusing on the OntoClean …
Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings
Concept embeddings offer a practical and efficient mechanism for injecting commonsense
knowledge into downstream tasks. Their core purpose is often not to predict the …
knowledge into downstream tasks. Their core purpose is often not to predict the …
AMenDeD: Modelling concepts by aligning mentions, definitions and decontextualised embeddings
Abstract Contextualised Language Models (LM) improve on traditional word embeddings by
encoding the meaning of words in context. However, such models have also made it …
encoding the meaning of words in context. However, such models have also made it …
[PDF][PDF] Beyond Optimal: Interactive Identification of Better-than-optimal Repairs
F Kriegel - 2025 - lat.inf.tu-dresden.de
Knowledge-based systems (KBS) represent complex domains in an explicit, structured
manner and comprise an inference engine that reasons about the domain to draw precise …
manner and comprise an inference engine that reasons about the domain to draw precise …
Beyond Optimal
F Kriegel - 2024 - tud.qucosa.de
Abstract (EN) We propose an interactive repair method for the description logic EL that is
based on the optimal-repair framework. The obtained repair might not be optimal in the …
based on the optimal-repair framework. The obtained repair might not be optimal in the …
[PDF][PDF] LTCS–Report
F Kriegel - lat.inf.tu-dresden.de
We present an FCA-based axiomatization method that produces a complete EL TBox (the
terminological part of an OWL 2 EL ontology) from a graph dataset in at most exponential …
terminological part of an OWL 2 EL ontology) from a graph dataset in at most exponential …