OAEI Machine Learning Dataset for Online Model Generation

TL;DR

This paper introduces a comprehensive dataset for OAEI that enables online model learning, allowing fair comparison of machine learning-based ontology matching systems by facilitating adaptive training and validation.

Contribution

The paper presents a new dataset for OAEI that supports online model learning, addressing fairness issues caused by offline training and subset sampling in existing evaluations.

Findings

Dataset enables online adaptation of models

Fine-tuning confidence thresholds improves system performance

Supports fair comparison of ML-based ontology matchers

Abstract

Ontology and knowledge graph matching systems are evaluated annually by the Ontology Alignment Evaluation Initiative (OAEI). More and more systems use machine learning-based approaches, including large language models. The training and validation datasets are usually determined by the system developer and often a subset of the reference alignments are used. This sampling is against the OAEI rules and makes a fair comparison impossible. Furthermore, those models are trained offline (a trained and optimized model is packaged into the matcher) and therefore the systems are specifically trained for those tasks. In this paper, we introduce a dataset that contains training, validation, and test sets for most of the OAEI tracks. Thus, online model learning (the systems must adapt to the given input alignment without human intervention) is made possible to enable a fair comparison for ML-based systems. We showcase the usefulness of the dataset by fine-tuning the confidence thresholds of popular systems.