Ontology Completion with Natural Language Inference and Concept Embeddings: An Analysis
This work addresses ontology completion, a generalization of taxonomy expansion, for knowledge representation and AI systems, but it is incremental as it compares existing approaches.
The paper tackles the problem of finding missing knowledge in ontologies by comparing Natural Language Inference (NLI) and concept embedding approaches, finding that hybrid strategies achieve the best results while the task remains highly challenging for Large Language Models.
We consider the problem of finding plausible knowledge that is missing from a given ontology, as a generalisation of the well-studied taxonomy expansion task. One line of work treats this task as a Natural Language Inference (NLI) problem, thus relying on the knowledge captured by language models to identify the missing knowledge. Another line of work uses concept embeddings to identify what different concepts have in common, taking inspiration from cognitive models for category based induction. These two approaches are intuitively complementary, but their effectiveness has not yet been compared. In this paper, we introduce a benchmark for evaluating ontology completion methods and thoroughly analyse the strengths and weaknesses of both approaches. We find that both approaches are indeed complementary, with hybrid strategies achieving the best overall results. We also find that the task is highly challenging for Large Language Models, even after fine-tuning.