BRUMS at SemEval-2020 Task 12 : Transformer based Multilingual Offensive Language Identification in Social Media

TL;DR

This paper presents BRUMS, a multilingual transformer-based deep learning model designed to identify offensive language across social media posts in five languages, demonstrating flexible and effective performance.

Contribution

The paper introduces a multilingual transformer model for offensive language detection that works across multiple languages with competitive results.

Findings

Achieved acceptable evaluation scores across five languages.

Demonstrated flexibility of the model in multilingual settings.

Showed effectiveness of transformer-based approach in social media offensive language detection.

Abstract

In this paper, we describe the team \textit{BRUMS} entry to OffensEval 2: Multilingual Offensive Language Identification in Social Media in SemEval-2020. The OffensEval organizers provided participants with annotated datasets containing posts from social media in Arabic, Danish, English, Greek and Turkish. We present a multilingual deep learning model to identify offensive language in social media. Overall, the approach achieves acceptable evaluation scores, while maintaining flexibility between languages.