Tekleab15/N-gram-Language-Models

A project to create and analyze n-gram language models using Amharic corpus # N-gram Language Models ## Project Overview This project involves creating and analyzing n-gram language models using an Amharic corpus. The tasks include generating n-grams, calculating probabilities, and visualizing results through word clouds. Additionally, the project includes intrinsic and extrinsic evaluation of the models using TensorFlow. ## Repository Structure - `data/`: Contains the corpus data files. - `notebooks/`: Contains Jupyter Notebooks with detailed analysis and code. - `scripts/`: Contains Python scripts for generating n-grams, calculating probabilities, visualizing word clouds, and evaluating models. - `results/`: Contains output results like generated sentences and word clouds. - `images/`: Contains any images or visualizations. ## Installation To run the project, ensure you have the following dependencies installed: ```bash pip install nltk pandas matplotlib wordcloud tensorflow