NLP — Roadmap

1. Classical NLP: Tokenization, POS Tagging, NER & Parsing

• Text normalization: tokenization, stemming, lemmatization
• Part-of-speech (POS) tagging
• Named Entity Recognition (NER)
• Syntactic parsing: dependency and constituency parsing

2. Word Embeddings

• word2vec: CBOW and skip-gram
• GloVe
• fastText and subword embeddings
• Why contextual embeddings (BERT) superseded static word embeddings

3. NLP Task Taxonomy

• Sequence labeling (BIO tagging)
• Text classification, sentiment analysis
• Machine translation: statistical MT to neural MT
• Summarization: extractive vs. abstractive
• Question answering: extractive vs. generative

Next: LLMs & GenAI — where this task taxonomy gets absorbed into general-purpose Transformer models.