In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN). Local information and global information interact through different layers of BERT, allowing them to influence mutually and to build together a final representation ...
We report 86.46% in terms of F1-score using this VGCN-BERT approach which allows us to obtain comparable results with the current state-of-the-art, ensemble BERT, so as to detect aggressive content regarding the track MEX-A3T 2020.
In particular, models using attention mechanism such as BERT have shown to have the capability of...doi:10.1007/978-3-030-45439-5_25Lu, ZhibinUniversity of MontrealDu, PanUniversity of MontrealNie, Jian-YunUniversity of Montreal