Offense Detection in Dravidian Languages using Code-Mixing Index based Focal Loss

TL;DR

This paper presents a novel approach for offensive language detection in Dravidian languages that effectively handles code-mixing, class imbalance, multilingualism, and mixed scripts using a new CMI-based focal loss and cosine classifier.

Contribution

The paper introduces a CMI-based focal loss and cosine classifier tailored for offensive detection in low-resource, code-mixed, and multilingual Dravidian languages, addressing key challenges.

Findings

Improved detection accuracy with the proposed CMI focal loss

Effective handling of code-mixed and mixed-script instances

Enhanced performance in low-resource multilingual settings

Abstract

Over the past decade, we have seen exponential growth in online content fueled by social media platforms. Data generation of this scale comes with the caveat of insurmountable offensive content in it. The complexity of identifying offensive content is exacerbated by the usage of multiple modalities (image, language, etc.), code-mixed language and more. Moreover, even after careful sampling and annotation of offensive content, there will always exist a significant class imbalance between offensive and non-offensive content. In this paper, we introduce a novel Code-Mixing Index (CMI) based focal loss which circumvents two challenges (1) code-mixing in languages (2) class imbalance problem for Dravidian language offense detection. We also replace the conventional dot product-based classifier with the cosine-based classifier which results in a boost in performance. Further, we use multilingual models that help transfer characteristics learnt across languages to work effectively with low resourced languages. It is also important to note that our model handles instances of mixed script (say usage of Latin and Dravidian-Tamil script) as well. To summarize, our model can handle offensive language detection in a low-resource, class imbalanced, multilingual and code-mixed setting.