TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Text Classification	TRAC2-Benghali. Task 2.	BERT	F1	0.929702403	# 1
Text Classification	TRAC2-English. Task2.	BERT	F1	0.871585052	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/bert-of-all-trades-master-of-some/text-classification-on-trac2-benghali-task-2)](https://paperswithcode.com/sota/text-classification-on-trac2-benghali-task-2?p=bert-of-all-trades-master-of-some)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/bert-of-all-trades-master-of-some/text-classification-on-trac2-english-task2)](https://paperswithcode.com/sota/text-classification-on-trac2-english-task2?p=bert-of-all-trades-master-of-some)`

BERT of all trades, master of some

LREC 2020 · Denis Gordeev, Olga Lykova ·

This paper describes our results for TRAC 2020 competition held together with the conference LREC 2020. Our team name was Ms8qQxMbnjJMgYcw. The competition consisted of 2 subtasks in 3 languages (Bengali, English and Hindi) where the participants{'} task was to classify aggression in short texts from social media and decide whether it is gendered or not. We used a single BERT-based system with two outputs for all tasks simultaneously. Our model placed first in English and second in Bengali gendered text classification competition tasks with 0.87 and 0.93 in F1-score respectively.

PDF Abstract