Do PLMs Know and Understand Ontological Knowledge?

TL;DR

This paper systematically investigates whether pretrained language models possess and understand ontological knowledge, including types, hierarchical relationships, and reasoning capabilities, revealing their partial but incomplete understanding.

Contribution

It introduces a comprehensive probing framework to assess PLMs' knowledge and understanding of ontological concepts and reasoning, filling a gap in prior factual knowledge studies.

Findings

PLMs can memorize some ontological facts.

PLMs can perform some logical reasoning with ontological knowledge.

Performance in memorization and reasoning is incomplete.

Abstract

Ontological knowledge, which comprises classes and properties and their relationships, is integral to world knowledge. It is significant to explore whether Pretrained Language Models (PLMs) know and understand such knowledge. However, existing PLM-probing studies focus mainly on factual knowledge, lacking a systematic probing of ontological knowledge. In this paper, we focus on probing whether PLMs store ontological knowledge and have a semantic understanding of the knowledge rather than rote memorization of the surface form. To probe whether PLMs know ontological knowledge, we investigate how well PLMs memorize: (1) types of entities; (2) hierarchical relationships among classes and properties, e.g., Person is a subclass of Animal and Member of Sports Team is a subproperty of Member of ; (3) domain and range constraints of properties, e.g., the subject of Member of Sports Team should be a Person and the object should be a Sports Team. To further probe whether PLMs truly understand ontological knowledge beyond memorization, we comprehensively study whether they can reliably perform logical reasoning with given knowledge according to ontological entailment rules. Our probing results show that PLMs can memorize certain ontological knowledge and utilize implicit knowledge in reasoning. However, both the memorizing and reasoning performances are less than perfect, indicating incomplete knowledge and understanding.