Boosting Adverse Drug Event Normalization on Social Media: General-Purpose Model Initialization and Biomedical Semantic Text Similarity Benefit Zero-Shot Linking in Informal Contexts

TL;DR

This paper introduces a novel approach for adverse drug event normalization on social media by leveraging general-purpose model initialization and semantic similarity fine-tuning, achieving state-of-the-art results.

Contribution

It proposes using general-purpose model initialization with BioLORD and semantic-text-similarity fine-tuning to improve adverse drug event normalization on social media.

Findings

Achieved state-of-the-art performance on social media datasets.

Demonstrated effectiveness of general-purpose initialization for biomedical tasks.

Potential to set a new benchmark for adverse drug event normalization.

Abstract

Biomedical entity linking, also known as biomedical concept normalization, has recently witnessed the rise to prominence of zero-shot contrastive models. However, the pre-training material used for these models has, until now, largely consisted of specialist biomedical content such as MIMIC-III clinical notes (Johnson et al., 2016) and PubMed papers (Sayers et al., 2021; Gao et al., 2020). While the resulting in-domain models have shown promising results for many biomedical tasks, adverse drug event normalization on social media texts has so far remained challenging for them (Portelli et al., 2022). In this paper, we propose a new approach for adverse drug event normalization on social media relying on general-purpose model initialization via BioLORD (Remy et al., 2022) and a semantic-text-similarity fine-tuning named STS. Our experimental results on several social media datasets demonstrate the effectiveness of our proposed approach, by achieving state-of-the-art performance. Based on its strong performance across all the tested datasets, we believe this work could emerge as a turning point for the task of adverse drug event normalization on social media and has the potential to serve as a benchmark for future research in the field.