This repository is where I learn and experiment with Natural Language Processing from the ground up.
The goal is to understand how NLP systems actually work by implementing ideas, testing them, and observing their behavior on real data.
- Small experiments to understand core NLP concepts
- Implementations of classical and modern techniques
- Model training on simple datasets
- Notes and observations from hands-on exploration
- Text preprocessing and normalization
- Tokenization techniques
- Vectorization (BoW, TF-IDF, embeddings)
- Sequence models (RNN/LSTM based approaches)
- Language modeling basics
- Practical NLP workflows
This is not a polished library.
It is a working space for learning, testing, and building intuition through practice.