Entity-Augmented Neuroscience Knowledge Retrieval Using Ontology and Semantic Understanding Capability of LLM

TL;DR

This paper introduces a novel approach to construct a neuroscience knowledge graph from unlabeled research texts using LLMs and ontologies, significantly improving knowledge retrieval and question answering in neuroscience.

Contribution

It presents a new method for building neuroscience knowledge graphs from unlabeled data leveraging LLMs, ontology, and embeddings, reducing reliance on labeled datasets.

Findings

Achieved an F1 score of 0.84 for entity extraction from unlabeled data.

Enhanced neuroscience question answering accuracy by over 52%.

Demonstrated comparable performance to supervised methods in entity and relation extraction.

Abstract

Neuroscience research publications encompass a vast wealth of knowledge. Accurately retrieving existing information and discovering new insights from this extensive literature is essential for advancing the field. However, when knowledge is dispersed across multiple sources, current state-of-the-art retrieval methods often struggle to extract the necessary information. A knowledge graph (KG) can integrate and link knowledge from multiple sources. However, existing methods for constructing KGs in neuroscience often rely on labeled data and require domain expertise. Acquiring large-scale, labeled data for a specialized area like neuroscience presents significant challenges. This work proposes novel methods for constructing KG from unlabeled large-scale neuroscience research corpus utilizing large language models (LLM), neuroscience ontology, and text embeddings. We analyze the semantic relevance of neuroscience text segments identified by LLM for building the knowledge graph. We also introduce an entity-augmented information retrieval algorithm to extract knowledge from the KG. Several experiments were conducted to evaluate the proposed approaches. The results demonstrate that our methods significantly enhance knowledge discovery from the unlabeled neuroscience research corpus. The performance of the proposed entity and relation extraction method is comparable to the existing supervised method. It achieves an F1 score of 0.84 for entity extraction from the unlabeled data. The knowledge obtained from the KG improves answers to over 52% of neuroscience questions from the PubMedQA dataset and questions generated using selected neuroscience entities.