Neuro-Conceptual Artificial Intelligence: Integrating OPM with Deep Learning to Enhance Question Answering Quality

TL;DR

This paper presents Neuro-Conceptual AI (NCAI), which combines Object-Process Methodology with deep learning to improve question-answering accuracy, reasoning transparency, and knowledge representation beyond traditional methods.

Contribution

The paper introduces NCAI, integrating OPM with deep learning for enhanced knowledge modeling and reasoning transparency in AI systems, surpassing traditional triplet-based knowledge graphs.

Findings

NCAI outperforms traditional QA methods in accuracy.

Proposes quantitative transparency metrics for reasoning evaluation.

Uses in-context learning to convert natural language into OPM models.

Abstract

Knowledge representation and reasoning are critical challenges in Artificial Intelligence (AI), particularly in integrating neural and symbolic approaches to achieve explainable and transparent AI systems. Traditional knowledge representation methods often fall short of capturing complex processes and state changes. We introduce Neuro-Conceptual Artificial Intelligence (NCAI), a specialization of the neuro-symbolic AI approach that integrates conceptual modeling using Object-Process Methodology (OPM) ISO 19450:2024 with deep learning to enhance question-answering (QA) quality. By converting natural language text into OPM models using in-context learning, NCAI leverages the expressive power of OPM to represent complex OPM elements-processes, objects, and states-beyond what traditional triplet-based knowledge graphs can easily capture. This rich structured knowledge representation improves reasoning transparency and answer accuracy in an OPM-QA system. We further propose transparency evaluation metrics to quantitatively measure how faithfully the predicted reasoning aligns with OPM-based conceptual logic. Our experiments demonstrate that NCAI outperforms traditional methods, highlighting its potential for advancing neuro-symbolic AI by providing rich knowledge representations, measurable transparency, and improved reasoning.