Matching with Transformers in MELT
This work addresses the need for more accurate automated matching in ontologies and knowledge graphs, which is incremental as it applies existing transformer models to a specific domain task.
The paper tackled the problem of matching ontologies and knowledge graphs by using transformer-based language models to capture textual meaning instead of simple lexical comparisons, resulting in a transformer-based filter that helps choose correct correspondences from high-recall alignments with good performance using simple post-processing methods.
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.