Kata.ai
Publication year: 2021

BERT Goes Brrr: A Venture Towards the Lesser Error in Classifying Medical Self-Reporters on Twitter

Written by:
Alham Fikri Aji, Haryo Akbarianto Wibowo, Made Nindyatama Nityasya, Radityo Eko Prasojo, Tirana Noor Fatyanosa

Abstract

This paper describes our team’s submission for the Social Media Mining for Health (SMM4H) 2021 shared task. We participated in three subtasks: Classifying adverse drug effect, COVID-19 self-report, and COVID-19 symptoms. Our system is based on BERT model pre-trained on the domain-specific text. In addition, we perform data cleaning and augmentation, as well as hyperparameter optimization and model ensemble to further boost the BERT performance. We achieved the first rank in both classifying adverse drug effects and COVID-19 self-report tasks.

  • Share
Download Full Paper

Other case Paper

BERT Goes Brrr: A Venture Towards the Lesser Error in Classifying Medical Self-Reporters on Twitter
Publication year: 2021

BERT Goes Brrr: A Venture Towards the Lesser Error in Classifying Medical Self-Reporters on Twitter

Benchmarking Multidomain English-Indonesian Machine Translation
Publication year: 2020

Benchmarking Multidomain English-Indonesian Machine Translation

Costs to Consider in Adopting NLP for Your Business
Publication year: 2020

Costs to Consider in Adopting NLP for Your Business

Ready to build your conversational AI?

Get started
CTA