Neural Networks for NLP

This repository contains a collection of Jupyter notebooks exploring neural network architectures for Natural Language Processing (NLP).
It was developed as part of coursework and self-study to practice fundamental and advanced concepts in deep learning for text.

---

📂 Repository Structure

• word_embeddings.ipynb — Introduction to word embeddings (Word2Vec, GloVe, embedding matrix analysis).
• lstm.ipynb — Language modeling with LSTM networks.
• gru.ipynb — Sequence modeling using GRU networks.
• language_modelling_lstm.ipynb — Hands-on example of language modeling with LSTM.
• bidirectional_rnn.ipynb — Implementation of bidirectional RNNs and analysis of embedding matrix evolution.
• data/ — Dataset(s) and preprocessed files used for experiments.
• README.md — Project documentation (this file).

---

🚀 Features & Goals

• Build and train RNN-based models for sequence and language modeling tasks.
• Compare different architectures: RNN, LSTM, GRU, Bidirectional RNN.
• Explore word embeddings and their evolution during training.
• Provide educational examples for learners interested in deep learning and NLP.