Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation

TL;DR

This paper explores cross-lingual few-shot and incremental learning techniques using multilingual models to perform high-accuracy sentiment analysis in Persian with limited data from diverse sources.

Contribution

It introduces a novel approach combining few-shot and incremental learning with multilingual models specifically for Persian sentiment analysis.

Findings

mDeBERTa and XLM-RoBERTa achieved 96% accuracy

Effective use of diverse data sources for model training

Demonstrates success of cross-lingual transfer in low-resource settings

Abstract

This research examines cross-lingual sentiment analysis using few-shot learning and incremental learning methods in Persian. The main objective is to develop a model capable of performing sentiment analysis in Persian using limited data, while getting prior knowledge from high-resource languages. To achieve this, three pre-trained multilingual models (XLM-RoBERTa, mDeBERTa, and DistilBERT) were employed, which were fine-tuned using few-shot and incremental learning approaches on small samples of Persian data from diverse sources, including X, Instagram, Digikala, Snappfood, and Taaghche. This variety enabled the models to learn from a broad range of contexts. Experimental results show that the mDeBERTa and XLM-RoBERTa achieved high performances, reaching 96% accuracy on Persian sentiment analysis. These findings highlight the effectiveness of combining few-shot learning and incremental learning with multilingual pre-trained models.