Assignment 1: Co-occurrence Matrix and Word Embeddings

This project implements count-based word embeddings using a co-occurrence matrix.
The implementation covers:

• Extracting distinct words (vocabulary) from a corpus
• Constructing a co-occurrence matrix with a sliding window
• Dimensionality reduction (SVD) to produce low-dimensional embeddings
• Plotting the resulting embeddings in 2D space

---

📂 Files

• Assisgnment1_22102.ipynb → Original Jupyter/Colab notebook version.

---

📦 Requirements

Install dependencies before running the script:

pip install nltk scikit-learn matplotlib