Module 1 · Introduction to NLP

OBJECTIVE: understand what Natural Language Processing (NLP) is, the main tasks it solves, and how text is cleaned and turned into numbers that a model can use. WHAT WE COVER: • What NLP is and where it is used every day • The main NLP tasks: classification, entity extraction (NER), search, question answering, summarisation, translation, text generation • Text preprocessing: tokens, lowercasing, stopwords, stemming and lemmatisation • Turning text into numbers: Bag of Words, TF-IDF, word embeddings (Word2Vec, GloVe) • Why older sequence models (RNN/LSTM) were replaced by Transformers • The main NLP tools: NLTK, spaCy, scikit-learn, Hugging Face AFTER THIS MODULE YOU CAN: • Name the right NLP task for a business problem • Clean text and convert it into TF-IDF features or word vectors • Explain why words need context — the reason Transformers exist MINI EXERCISE: explore 1,000 movie reviews (IMDB) — clean them, find the top words, compare TF-IDF terms for positive vs negative, and find similar words with GloVe.