⚡ CrackLab
📝

NLP Foundations

Natural Language Processing: tokenization, BoW, TF-IDF, NER, POS tagging

1

What is NLP — Pipeline Overview

beginner~18min

NLP definition, applications, end-to-end pipeline from raw text to insight

2

Text Preprocessing: Tokenization, Stopwords, Stemming, Lemmatization

beginner~18min

Cleaning text data step by step with NLTK and spaCy

3

Bag of Words (BoW)

beginner~18min

Document-term matrix, sparse representation, limitations

4

TF-IDF (Term Frequency-Inverse Document Frequency)

intermediate~28min

Weighting words by importance, formula, implementation

5

Named Entity Recognition (NER) with spaCy

intermediate~28min

Entity extraction, custom entity tagging with set_ents, practical demo

6

Part of Speech (POS) Tagging

intermediate~28min

Grammatical roles, noun/verb/adjective identification, use cases

7

N-Gram Language Models

intermediate~28min

Unigrams, bigrams, trigrams, perplexity, simple language modeling

8

NLP Pipeline — End to End Practical

intermediate~28min

Building a complete text processing pipeline from raw data to features