NeuroSym-BioCAT: Leveraging Neuro-Symbolic Methods for Biomedical Scholarly Document Categorization and Question Answering

TL;DR

This paper presents a neuro-symbolic approach combining optimized topic modeling and a fine-tuned MiniLM model to improve biomedical document categorization and question answering, achieving high accuracy with efficient models.

Contribution

It introduces OVB-LDA and BI-POP CMA-ES for better document categorization and demonstrates that a compact MiniLM model can effectively extract answers in biomedical contexts.

Findings

Outperforms established methods like RYGH and bio-answer finder.

High accuracy achieved using only abstracts for biomedical QA.

MiniLM's competitive performance challenges the need for large models.

Abstract

The growing volume of biomedical scholarly document abstracts presents an increasing challenge in efficiently retrieving accurate and relevant information. To address this, we introduce a novel approach that integrates an optimized topic modelling framework, OVB-LDA, with the BI-POP CMA-ES optimization technique for enhanced scholarly document abstract categorization. Complementing this, we employ the distilled MiniLM model, fine-tuned on domain-specific data, for high-precision answer extraction. Our approach is evaluated across three configurations: scholarly document abstract retrieval, gold-standard scholarly documents abstract, and gold-standard snippets, consistently outperforming established methods such as RYGH and bio-answer finder. Notably, we demonstrate that extracting answers from scholarly documents abstracts alone can yield high accuracy, underscoring the sufficiency of abstracts for many biomedical queries. Despite its compact size, MiniLM exhibits competitive performance, challenging the prevailing notion that only large, resource-intensive models can handle such complex tasks. Our results, validated across various question types and evaluation batches, highlight the robustness and adaptability of our method in real-world biomedical applications. While our approach shows promise, we identify challenges in handling complex list-type questions and inconsistencies in evaluation metrics. Future work will focus on refining the topic model with more extensive domain-specific datasets, further optimizing MiniLM and utilizing large language models (LLM) to improve both precision and efficiency in biomedical question answering.