Sentiment Classification for Low-Resource Indian Languages Using Multilingual Transformers and Parameter-Efficient Fine-Tuning

Key Points

• The aim is to assess effective sentiment classification methods for low-resource Indian languages utilizing advanced multilingual models.
• Evaluated the performance of multilingual transformers in sentiment classification.
• Applied parameter-efficient fine-tuning techniques to enhance model training.
• Focused on low-resource Indian languages for analysis.
• Demonstrated improved sentiment classification accuracy for low-resource languages.
• Highlighted the effectiveness of parameter-efficient fine-tuning in achieving better performance.