S. Chowdhury

Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling

This work evaluates four omni LLMs in a zero-shot setting and shows that fine-tuning consistently outperforms zero-shot inference, and explores synthetic data augmentation by using an LLM to generate culturally grounded Tunisian Derja utterances, followed by voice cloning to generate synthetic speech.