An implementation of a classic N-Gram Language Model from scratch using PyTorch. This project covers word embeddings, perplexity evaluation, and t-SNE visualization for text generation.
-
Updated
Aug 9, 2025 - Jupyter Notebook
An implementation of a classic N-Gram Language Model from scratch using PyTorch. This project covers word embeddings, perplexity evaluation, and t-SNE visualization for text generation.
An end-to-end NLP pipeline for legal documents, including OCR-based text extraction, neural language modeling from scratch (NumPy), sentence and document embeddings, extractive and abstractive summarization, grammar refinement, and semantic case similarity retrieval using cosine similarity.
Add a description, image, and links to the nlp-from-scratch topic page so that developers can more easily learn about it.
To associate your repository with the nlp-from-scratch topic, visit your repo's landing page and select "manage topics."