nlp-notebooks

Why we included this project

Anyone teaching themselves applied natural language processing will find this collection a solid hands-on companion, because each notebook works through a concrete task from start to finish instead of just describing a technique. The coverage is wide: word embeddings, topic modeling, named entity recognition, text and intent classification, sentence similarity, and cross-lingual transfer. That range works as a structured path for newcomers and as a reference for seeing how different libraries handle the same job, from spaCy and scikit-learn to a BERT model in PyTorch. Since classical methods such as CRFs and LDA sit next to transformer-based ones, you can judge older and newer approaches against each other in one place. This is a curated learning resource rather than production software, so treat it as a study path and recipe book, not something to wire directly into a live pipeline.