Resource Description Framework
PulseAugur coverage of Resource Description Framework — every cluster mentioning Resource Description Framework across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
PhD opportunity at Inria Côte d’Azur in Knowledge Graphs and NLP
A PhD opportunity is available at the WIMMICS team at Inria Côte d’Azur, focusing on the intersection of Knowledge Graphs, Semantic Web, and Natural Language Processing (NLP). The research will involve extracting inform…
-
New GNN4PPM approach enhances predictive process monitoring with R-GCNs
Researchers have developed GNN4PPM, a novel approach for Predictive Process Monitoring (PPM) that utilizes Relational Graph Convolutional Networks (R-GCNs). This method represents event log data as a heterogeneous knowl…
-
Build Zero-Hallucination AI Inference Engines with TypeScript
This article details how to build zero-hallucination inference engines using TypeScript by combining the json-rules-engine and N3 Reasoner. It addresses the fundamental limitation of Large Language Models in handling st…
-
Beyond Vector Search: Semantic Graphs for Zero-Hallucination AI
This article argues for a shift from probabilistic AI methods like vector stores and RAG to deterministic semantic querying using knowledge graphs, SPARQL, and RDF. It highlights the limitations of vector stores in hand…
-
Neuro-Symbolic AI Combats LLM Hallucinations with Semantic Web Standards
Large Language Models (LLMs) are prone to generating fictional information, a significant risk for enterprise applications. To combat this, a neuro-symbolic AI approach is emerging, which combines LLMs with symbolic kno…
-
zbMATH Open Knowledge Graph maps 250 years of math research
Researchers have developed the zbMATH Open Knowledge Graph, an extensive RDF knowledge graph that spans over 250 years of mathematical research. This graph goes beyond typical bibliographic and citation data by incorpor…
-
New infrastructure enhances trust in manufacturing knowledge graphs
Researchers have developed a composable trust infrastructure designed to enhance the reliability of manufacturing knowledge graphs. This system integrates four key capabilities: SHACL validation, PROV-O provenance, doma…
-
Author criticizes slow pace of RDF and SHACL standards development
The author argues that standards work, particularly for technologies like RDF and SHACL, is often too slow due to lengthy processes involving mailing lists, issue threads, and meetings. They emphasize the need for these…
-
New framework integrates RDF with Differential Dynamic Logic for AI systems
Researchers have developed RDFdL, a novel framework that combines Resource Description Framework (RDF) with Differential Dynamic Logic (dL). This integration aims to bridge the gap in representing and reasoning about bo…
-
New platform enables machine learning on visual web page representations
Researchers have developed a new platform to enable machine learning applications on web pages by capturing their visual and structural properties. This platform uses the FitLayout tool to render web pages, storing thei…
-
New SC2R Framework Offers Semantically Validated Interventions for At-Risk Students
This paper introduces SC2R, a framework designed to provide actionable and constraint-aware interventions for students at risk of poor academic performance. SC2R integrates a predictive model with an integer-programming…
-
New SC2R framework offers semantically feasible interventions for at-risk students
Researchers have developed SC2R, a new framework designed to provide actionable and constraint-aware interventions for students identified as at risk of poor academic performance. This system combines predictive modelin…
-
AutoSchema framework enables AI agents to query diverse knowledge graphs without training
Researchers have developed AutoSchema, a novel framework designed to enable language model agents to query heterogeneous knowledge graphs without prior training. This system addresses the challenge of varying schemas, i…
-
New method integrates OWL axioms into SHACL constraints for efficient RDF graph validation
Researchers have developed a new method to integrate OWL axioms directly into SHACL constraints, simplifying the process of validating RDF graphs that incorporate OWL ontologies. This approach constructs a translation t…
-
New BDI Ontology Formalizes AI Agency and Cognitive Modeling
Researchers have developed a formal Belief-Desire-Intention (BDI) ontology to better represent rational agency in artificial intelligence and cognitive sciences. This ontology aims to bridge the gap between cognitive ar…
-
New benchmark suite evaluates LLMs for translating natural language to SHACL
Researchers have introduced NL2SHACL-Bench, a new benchmark suite designed to evaluate the translation of natural language requirements into SHACL shapes for validating RDF knowledge graphs. The benchmark was used to as…
-
New chain stratification method improves RDF rules with negation
Researchers have introduced a novel method called chain stratification to address the complexities of incorporating default negation into RDF rule languages like N3 and SHACL Rules. Existing approaches often falter due …
-
New framework simplifies data quality analysis for domain experts
Researchers have developed a new framework called the Quality Pattern Model (QPM) to help domain experts define data quality analyses without needing deep technical expertise. QPM uses technology-independent query templ…
-
New ISONGraph format slashes token use, boosts LLM knowledge graph accuracy
A new graph serialization format called ISONGraph has been developed to improve the efficiency of knowledge graphs used with Large Language Models (LLMs). The format was found to reduce token count by approximately 70% …
-
Neuro-Symbolic Meta-Policy Enhances Partial Observability in Reinforcement Learning
Researchers have developed a novel neuro-symbolic meta-policy designed to enhance decision-making in partially observable reinforcement learning scenarios. This system intelligently manages symbolic memory by learning w…