Battling Hateful Content in Indic Languages HASOC '21

TL;DR

This paper addresses hate speech detection in multilingual and code-mixed social media texts using transformer models, achieving a top-three ranking in the HASOC 2021 challenge.

Contribution

It introduces a multilingual transformer-based approach tailored for hate speech detection across six subtasks in a multilingual Twitter dataset.

Findings

Achieved 3rd place overall in the challenge

Effective handling of code-mixed and multilingual texts

Demonstrated the viability of transformer models for hate speech detection

Abstract

The extensive rise in consumption of online social media (OSMs) by a large number of people poses a critical problem of curbing the spread of hateful content on these platforms. With the growing usage of OSMs in multiple languages, the task of detecting and characterizing hate becomes more complex. The subtle variations of code-mixed texts along with switching scripts only add to the complexity. This paper presents a solution for the HASOC 2021 Multilingual Twitter Hate-Speech Detection challenge by team PreCog IIIT Hyderabad. We adopt a multilingual transformer based approach and describe our architecture for all 6 subtasks as part of the challenge. Out of the 6 teams that participated in all the subtasks, our submissions rank 3rd overall.