Matching with Transformers in MELT

TL;DR

This paper explores the use of transformer-based models for ontology and knowledge graph matching, framing it as a classification task, and provides a practical implementation within the MELT framework that improves matching accuracy.

Contribution

It introduces transformer-based approaches for ontology matching, modeling the task as classification, and offers an accessible implementation in the MELT framework.

Findings

Transformer models improve matching accuracy over traditional methods.

A transformer-based filter effectively selects correct correspondences.

Simple post-processing yields strong alignment results.

Abstract

One of the strongest signals for automated matching of ontologies and knowledge graphs are the textual descriptions of the concepts. The methods that are typically applied (such as character- or token-based comparisons) are relatively simple, and therefore do not capture the actual meaning of the texts. With the rise of transformer-based language models, text comparison based on meaning (rather than lexical features) is possible. In this paper, we model the ontology matching task as classification problem and present approaches based on transformer models. We further provide an easy to use implementation in the MELT framework which is suited for ontology and knowledge graph matching. We show that a transformer-based filter helps to choose the correct correspondences given a high-recall alignment and already achieves a good result with simple alignment post-processing methods.