Search papers, labs, and topics across Lattice.
This paper introduces OntoLearner, a modular Python library designed to unify ontology learning processes by integrating large language models (LLMs) with standardized evaluation practices and ontology access. The study reveals that the primary challenge in ontology learning is not the sophistication of models but rather a structural mismatch between model knowledge encoding and ontology organization, as demonstrated through a large-scale evaluation of 22 retrieval models and 12 LLMs across various tasks. By providing 180 machine-readable ontologies and pipeline-ready datasets, OntoLearner facilitates systematic research and benchmarking in ontology learning, potentially accelerating advancements in the field.
The central challenge of ontology learning isn't model sophistication but rather how knowledge is structured and encoded, as revealed by a comprehensive evaluation using OntoLearner.
Ontology learning (OL) aims to automatically construct structured knowledge models from text, yet progress remains fragmented across methods, domains, and evaluation practices. Despite decades of research, OL lacks a shared infrastructure for systematic evaluation and ontology access. This absence has hindered progress and fragmented research, leaving the central challenges of OL largely unaddressed. We introduce OntoLearner, a modular, cross-domain, and first-of-its-kind framework that unifies ontology access, large language model (LLM)-driven learning pipelines, and standardized benchmarking. OntoLearner releases 180 machine-readable ontologies spanning 22 domains and provides pipeline-ready datasets with train/dev/test splits for three core OL tasks: term typing, taxonomy discovery, and non-taxonomic relation extraction. Using this infrastructure, we conduct a large-scale empirical study of OL, evaluating 22 retrieval models and 12 LLMs across domains and tasks. The results converge on a finding that reframes the central challenge of OL: failure modes scale with ontological complexity rather than model size or architectural sophistication. The primary bottleneck is not model capability, but a structural mismatch between how models encode knowledge and how ontologies organize it. These findings establish that effective OL is reachable through the cross-domain, multi-task benchmarking enabled by OntoLearner. OntoLearner is open-source (MIT license) at https://github.com/sciknoworg/OntoLearner/.
