Skip to content
SDB

AI Tutorials

Natural Language Processing

Master NLP from first principles — covering the full pipeline from tokenization, morphology, syntax, semantics, and discourse to text classification, NER, machine translation, QA, summarization, and production deployment with monitoring.

13 chapters · 371 min

← All AI tutorials

From text preprocessing and phonology to transformers, QA, and production deployment

  1. Ch. 01

    Introduction & Text Preprocessing

    The NLP pipeline, text normalization, tokenization, stemming, and lemmatization

    beginner · 28 min

    Read →
  2. Ch. 02

    Phonology & Speech Processing

    Phonemes, automatic speech recognition, speech-to-text, and text-to-speech systems

    intermediate · 25 min

    Read →
  3. Ch. 03

    Morphology & Lexical Analysis

    Word structure, morphemes, POS tagging, chunking, and lexical resources

    beginner · 25 min

    Read →
  4. Ch. 04

    Syntactic Analysis & Parsing

    Context-free grammars, constituency trees, dependency parsing, and grammar checking

    intermediate · 28 min

    Read →
  5. Ch. 05

    Semantic Analysis

    Word meaning, semantic similarity, word sense disambiguation, and semantic role labeling

    intermediate · 28 min

    Read →
  6. Ch. 06

    Discourse & Pragmatics

    Coreference resolution, discourse structure, speech acts, sarcasm, and pragmatic interpretation

    intermediate · 22 min

    Read →
  7. Ch. 07

    Text Representation & Embeddings

    From bag-of-words and TF-IDF to Word2Vec, GloVe, FastText, and contextual BERT embeddings

    intermediate · 32 min

    Read →
  8. Ch. 08

    Text Classification & Sentiment Analysis

    Spam detection, sentiment analysis, topic classification, and zero-shot approaches

    intermediate · 30 min

    Read →
  9. Ch. 09

    Information Extraction & NER

    Named entity recognition, relation extraction, event extraction, and knowledge base population

    intermediate · 28 min

    Read →
  10. Ch. 10

    Machine Translation

    From statistical phrase-based MT to neural seq2seq, attention, and Transformer-based translation

    advanced · 30 min

    Read →
  11. Ch. 11

    Question Answering & Summarization

    Extractive and abstractive QA, reading comprehension, RAG, and neural summarization

    advanced · 32 min

    Read →
  12. Ch. 12

    NLP Models: N-grams to Transformers

    Language modeling from n-gram statistics to RNNs, LSTMs, attention, and large language models

    advanced · 35 min

    Read →
  13. Ch. 13

    NLP Evaluation & Deployment

    Intrinsic and extrinsic evaluation, NLP benchmarks, production deployment, and model monitoring

    intermediate · 28 min

    Read →