Xiangyang Li, Yu Xia, Xiang Long, Z. Li, Sujian Li
CONSTRAINT@AAAI, 2021
In this paper, we describe our system for the AAAI 2021 shared task of COVID-19 Fake News Detection in English, where we achieved the 3rd position with the weighted \(F_1\) score of 0.9859 on the test set. Specifically, we proposed an ensemble method of different pre-trained language models such as BERT, Roberta, Ernie, etc. with various training strategies including warm-up, learning rate schedule and k-fold cross-validation. We also conduct an extensive analysis of the samples that are not correctly classified. The code is available at: https://github.com/archersama/3rd-solution-COVID19-Fake-News-Detection-in-English.
Cited by 2 publications.
Field of study: Computer Science