English

Language Model Analysis for Ontology Subsumption Inference

Computation and Language 2023-05-09 v3 Artificial Intelligence Logic in Computer Science

Abstract

Investigating whether pre-trained language models (LMs) can function as knowledge bases (KBs) has raised wide research interests recently. However, existing works focus on simple, triple-based, relational KBs, but omit more sophisticated, logic-based, conceptualised KBs such as OWL ontologies. To investigate an LM's knowledge of ontologies, we propose OntoLAMA, a set of inference-based probing tasks and datasets from ontology subsumption axioms involving both atomic and complex concepts. We conduct extensive experiments on ontologies of different domains and scales, and our results demonstrate that LMs encode relatively less background knowledge of Subsumption Inference (SI) than traditional Natural Language Inference (NLI) but can improve on SI significantly when a small number of samples are given. We will open-source our code and datasets.

Keywords

Cite

@article{arxiv.2302.06761,
  title  = {Language Model Analysis for Ontology Subsumption Inference},
  author = {Yuan He and Jiaoyan Chen and Ernesto Jiménez-Ruiz and Hang Dong and Ian Horrocks},
  journal= {arXiv preprint arXiv:2302.06761},
  year   = {2023}
}

Comments

Accepted at Findings of ACL 2023; OntoLAMA Datasets are available at: https://huggingface.co/datasets/krr-oxford/OntoLAMA (Huggingface) or https://doi.org/10.5281/zenodo.6480540 (Zenodo)

R2 v1 2026-06-28T08:39:24.043Z