DS4DH at #SMM4H 2023: Zero-Shot Adverse Drug Events Normalization using Sentence Transformers and Reciprocal-Rank Fusion

TL;DR

This paper presents a zero-shot approach for adverse drug event normalization in social media, combining sentence transformers and reciprocal-rank fusion, achieving top performance in the SMM4H 2023 shared task.

Contribution

The study introduces a novel two-stage system using BERT fine-tuning and zero-shot normalization with sentence transformers, outperforming existing methods in adverse drug event normalization.

Findings

Achieved an F1-score of 42.6%, outperforming the median by 10%.

Demonstrated the highest performance among all participants.

Validated the effectiveness of zero-shot normalization in social media text mining.

Abstract

This paper outlines the performance evaluation of a system for adverse drug event normalization, developed by the Data Science for Digital Health (DS4DH) group for the Social Media Mining for Health Applications (SMM4H) 2023 shared task 5. Shared task 5 targeted the normalization of adverse drug event mentions in Twitter to standard concepts of the Medical Dictionary for Regulatory Activities terminology. Our system hinges on a two-stage approach: BERT fine-tuning for entity recognition, followed by zero-shot normalization using sentence transformers and reciprocal-rank fusion. The approach yielded a precision of 44.9%, recall of 40.5%, and an F1-score of 42.6%. It outperformed the median performance in shared task 5 by 10% and demonstrated the highest performance among all participants. These results substantiate the effectiveness of our approach and its potential application for adverse drug event normalization in the realm of social media text mining.