BCH-NLP at BioCreative VII Track 3: medications detection in tweets using transformer networks and multi-task learning

TL;DR

This paper describes a transformer-based multi-task learning approach for detecting medication names in tweets, achieving top performance in the BioCreative VII challenge.

Contribution

The paper introduces a multi-task learning model with ensemble and data augmentation techniques for improved medication detection in social media texts.

Findings

Achieved a strict F1 score of 80.4, ranking first in the challenge.

Ensemble, multi-task learning, and data augmentation improve detection accuracy.

Model outperforms all other participants by over 10 points.

Abstract

In this paper, we present our work participating in the BioCreative VII Track 3 - automatic extraction of medication names in tweets, where we implemented a multi-task learning model that is jointly trained on text classification and sequence labelling. Our best system run achieved a strict F1 of 80.4, ranking first and more than 10 points higher than the average score of all participants. Our analyses show that the ensemble technique, multi-task learning, and data augmentation are all beneficial for medication detection in tweets.