A Language Model based Framework for New Concept Placement in Ontologies

TL;DR

This paper presents a neural network-based framework for inserting new concepts into ontologies, utilizing PLMs and LLMs for candidate search, edge formation, and selection, with evaluations on biomedical datasets.

Contribution

It introduces a multi-step approach leveraging neural methods and contrastive learning for ontology extension, including explainable instruction tuning for LLMs.

Findings

Fine-tuned PLMs excel in candidate search.

Multi-label Cross-encoder improves edge selection.

Explainable instruction tuning enhances LLM performance.

Abstract

We investigate the task of inserting new concepts extracted from texts into an ontology using language models. We explore an approach with three steps: edge search which is to find a set of candidate locations to insert (i.e., subsumptions between concepts), edge formation and enrichment which leverages the ontological structure to produce and enhance the edge candidates, and edge selection which eventually locates the edge to be placed into. In all steps, we propose to leverage neural methods, where we apply embedding-based methods and contrastive learning with Pre-trained Language Models (PLMs) such as BERT for edge search, and adapt a BERT fine-tuning-based multi-label Edge-Cross-encoder, and Large Language Models (LLMs) such as GPT series, FLAN-T5, and Llama 2, for edge selection. We evaluate the methods on recent datasets created using the SNOMED CT ontology and the MedMentions entity linking benchmark. The best settings in our framework use fine-tuned PLM for search and a multi-label Cross-encoder for selection. Zero-shot prompting of LLMs is still not adequate for the task, and we propose explainable instruction tuning of LLMs for improved performance. Our study shows the advantages of PLMs and highlights the encouraging performance of LLMs that motivates future studies.