Bagging BERT Models for Robust Aggression Identification
Published in
Workshop on Trolling, Aggression and Cyberbullying(2020)External Links:
TL
TL;DR
An ensemble of multiple fine-tuned BERT models based on bootstrap aggregating (bagging) is proposed and presented, finding that the F1-score drastically increases when ensembling up to 15 models, but the returns diminish for more models.