Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages

TL;DR

This paper explores using GPT-3.5 Turbo with prompt engineering to identify language at the word level in code-mixed Dravidian languages, addressing challenges posed by under-representation and complex morphology.

Contribution

It introduces a prompt-based approach leveraging GPT-3.5 Turbo for word-level language identification in low-resource Dravidian languages, demonstrating its effectiveness.

Findings

Kannada model outperforms Tamil model in accuracy

GPT-3.5 Turbo effectively classifies code-mixed words

Performance varies between languages, indicating room for improvement

Abstract

Language Identification (LI) is crucial for various natural language processing tasks, serving as a foundational step in applications such as sentiment analysis, machine translation, and information retrieval. In multilingual societies like India, particularly among the youth engaging on social media, text often exhibits code-mixing, blending local languages with English at different linguistic levels. This phenomenon presents formidable challenges for LI systems, especially when languages intermingle within single words. Dravidian languages, prevalent in southern India, possess rich morphological structures yet suffer from under-representation in digital platforms, leading to the adoption of Roman or hybrid scripts for communication. This paper introduces a prompt based method for a shared task aimed at addressing word-level LI challenges in Dravidian languages. In this work, we leveraged GPT-3.5 Turbo to understand whether the large language models is able to correctly classify words into correct categories. Our findings show that the Kannada model consistently outperformed the Tamil model across most metrics, indicating a higher accuracy and reliability in identifying and categorizing Kannada language instances. In contrast, the Tamil model showed moderate performance, particularly needing improvement in precision and recall.