This repository contains a collection of Natural Language Processing (NLP) projects exploring various techniques and applications in the field of computational linguistics and text processing.

A comprehensive implementation for detecting hate speech and offensive content in Vietnamese text data. The project uses state-of-the-art Vietnamese language models (PhoBERT and ViSoBERT) for text classification.

Key Features:

• Text preprocessing and normalization for Vietnamese
• Data augmentation techniques (EDA and LLM-based)
• Fine-tuning of pretrained Vietnamese language models
• Class imbalance handling with Focal Loss