nlp

This repository contains a series of NLP experiments and implementations. Key capabilities include: - Word Vector Models: Implementations of Continuous Bag of Words (CBOW) and Skip-gram, including training scripts and example generators. - Text Processing: Tools for tokenization, vocabulary mapping, and reading data from the BNC corpus. - Classical NLP: Implementation of the tf-idf algorithm and n-gram table construction/generation based on Jurafsky and Martin exercises. - Advanced Models: A tutorial implementation of a Transformer model using PyTorch and an implementation of the distance-dependent Chinese Restaurant Process (CRP). - Utility: A command-pattern framework for structuring programs with command-line interfaces.