IIITT@Dravidian-CodeMix-FIRE2021: Transliterate or translate? Sentiment analysis of code-mixed text in Dravidian languages

TL;DR

This paper explores sentiment analysis of code-mixed social media comments in Dravidian languages using pre-trained models, transliteration, and translation, achieving competitive rankings in a shared task at FIRE 2021.

Contribution

It presents a novel approach combining multilingual models, transliteration, and translation for sentiment analysis in Dravidian languages, addressing the challenge of code-mixed text.

Findings

Best models ranked 4th, 5th, and 10th in Tamil, Kannada, and Malayalam tasks.

Utilized fine-tuned ULMFiT and multilingual BERT models.

Demonstrated the effectiveness of combining transliteration and translation techniques.

Abstract

Sentiment analysis of social media posts and comments for various marketing and emotional purposes is gaining recognition. With the increasing presence of code-mixed content in various native languages, there is a need for ardent research to produce promising results. This research paper bestows a tiny contribution to this research in the form of sentiment analysis of code-mixed social media comments in the popular Dravidian languages Kannada, Tamil and Malayalam. It describes the work for the shared task conducted by Dravidian-CodeMix at FIRE 2021 by employing pre-trained models like ULMFiT and multilingual BERT fine-tuned on the code-mixed dataset, transliteration (TRAI) of the same, English translations (TRAA) of the TRAI data and the combination of all the three. The results are recorded in this research paper where the best models stood 4th, 5th and 10th ranks in the Tamil, Kannada and Malayalam tasks respectively.