Automated and Explainable Ontology Extension Based on Deep Learning: A Case Study in the Chemical Domain
This work addresses the scalability issue in ontology development for the chemical domain, though it is incremental as it builds on prior methods.
The authors tackled the problem of scaling manual ontology construction by developing an automated method for extending the ChEBI chemical ontology using a Transformer-based deep learning model, achieving an F1 score of 0.80, which is a 6 percentage point improvement over previous results.
Reference ontologies provide a shared vocabulary and knowledge resource for their domain. Manual construction enables them to maintain a high quality, allowing them to be widely accepted across their community. However, the manual development process does not scale for large domains. We present a new methodology for automatic ontology extension and apply it to the ChEBI ontology, a prominent reference ontology for life sciences chemistry. We trained a Transformer-based deep learning model on the leaf node structures from the ChEBI ontology and the classes to which they belong. The model is then capable of automatically classifying previously unseen chemical structures. The proposed model achieved an overall F1 score of 0.80, an improvement of 6 percentage points over our previous results on the same dataset. Additionally, we demonstrate how visualizing the model's attention weights can help to explain the results by providing insight into how the model made its decisions.