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

Published in arXiv preprint arXiv:2111.13726, 2021

Recommended citation: Dongfang Xu, Shan Chen, and Timothy Miller. 2021. BCH-NLP at BioCreative VII Track 3: medications detection in tweets using transformer networks and multi-task learning. In arXiv preprint arXiv:2111.13726. https://arxiv.org/pdf/2111.13726

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.