Multilingual Joint Fine-tuning of Transformer models for identifying Trolling, Aggression and Cyberbullying at TRAC 2020

Sudhanshu Mishra, Shivangi Prasad, Shubhanshu Mishra


Abstract
We present our team ‘3Idiots’ (referred as ‘sdhanshu’ in the official rankings) approach for the Trolling, Aggression and Cyberbullying (TRAC) 2020 shared tasks. Our approach relies on fine-tuning various Transformer models on the different datasets. We also investigated the utility of task label marginalization, joint label classification, and joint training on multilingual datasets as possible improvements to our models. Our team came second in English sub-task A, a close fourth in the English sub-task B and third in the remaining 4 sub-tasks. We find the multilingual joint training approach to be the best trade-off between computational efficiency of model deployment and model’s evaluation performance. We open source our approach at https://github.com/socialmediaie/TRAC2020.
Anthology ID:
2020.trac-1.19
Volume:
Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying
Month:
May
Year:
2020
Address:
Marseille, France
Venues:
LREC | TRAC | WS
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
120–125
Language:
English
URL:
https://www.aclweb.org/anthology/2020.trac-1.19
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.trac-1.19.pdf