Skip to content
conftrace_
2020 COLING COLING 2020

Medication Mention Detection in Tweets Using ELECTRA Transformers and Decision Trees

Abstract

AbstractThis study describes our proposed model design for the SMM4H 2020 Task 1. We fine-tune ELECTRA transformers using our trained SVM filter for data augmentation, along with decision trees to detect medication mentions in tweets. Our best F1-score of 0.7578 exceeded the mean score 0.6646 of all 15 submitting teams.

Authors

Lung-Hao Lee, Po-Han Chen, Hao-Chuan Kao, Ting-Chun Hung, Po-Lei Lee, Kuo-Kai Shyu

Topics

Machine Learning > Core Methods > Classification Deep Learning > Architectures > Transformers

Keywords

data augmentation named entity recognition decision tree medication mention
Download PDF

More from COLING 2020

All COLING 2020 papers →
Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa
Detecting Tweets Reporting Birth Defect Pregnancy Outcome Using Two-View CNN RNN Based Architecture
Identification of Medication Tweets Using Domain-specific Pre-trained Language Models
LITL at SMM4H: An Old-school Feature-based Classifier for Identifying Adverse Effects in Tweets
Sentence Classification with Imbalanced Data for Health Applications
HITSZ-ICRC: A Report for SMM4H Shared Task 2020-Automatic Classification of Medications and Adverse Effect in Tweets