Get Started

NLP: Foundations to Advanced

Language is the interface to intelligence.

29 lessonsAbout 31 hoursExpert level15 free lessonsBy AI engineering expert Rohit Ghumare
Start this phase
0 of 29 done
  1. 01Text Processing, Tokenization, Stemming, LemmatizationLanguage is continuous. Models are discrete. Preprocessing is the bridge.45 minutesBuildPythonFree lesson
  2. 02Bag of Words, TF-IDF, and Text RepresentationCount first, think later. TF-IDF still beats embeddings on well-defined tasks in 2026.75 minutesBuildPythonFree lesson
  3. 03Word Embeddings, Word2Vec from ScratchA word is the company it keeps. Train a shallow net on that idea and geometry falls out.75 minutesBuildPythonFree lesson
  4. 04GloVe, FastText, and Subword EmbeddingsWord2Vec trained one embedding per word. GloVe factorized the co-occurrence matrix. FastText embedded the pieces. BPE bridged to transformers.45 minutesBuildPythonFree lesson
  5. 05Sentiment AnalysisThe canonical NLP task. Most of what you need to know about classical text classification shows up here.75 minutesBuildPythonFree lesson
  6. 06Named Entity RecognitionPull the names out. Sounds easy until you deal with ambiguous boundaries, nested entities, and domain jargon.75 minutesBuildPythonFree lesson
  7. 07POS Tagging and Syntactic ParsingGrammar was unfashionable for a while. Then every LLM pipeline needed to validate structured extraction, and it came back.45 minutesBuildPythonFree lesson
  8. 08CNNs and RNNs for TextConvolutions learn n-grams. Recurrences remember. Both are superseded by attention. Both still matter on constrained hardware.75 minutesBuildPythonFree lesson
  9. 09Sequence-to-Sequence ModelsTwo RNNs pretending to be a translator. The bottleneck they hit is the reason attention exists.75 minutesBuildPythonFree lesson
  10. 10Attention Mechanism, The BreakthroughThe decoder stops squinting at a compressed summary and starts looking at the whole source. Everything after this is attention plus engineering.45 minutesBuildPythonFree lesson
  11. 11Machine TranslationTranslation is the task that paid for NLP research for thirty years and keeps paying now.75 minutesBuildPythonFree lesson
  12. 12Text SummarizationExtractive systems tell you what the document said. Abstractive systems tell you what the author meant. Different tasks, different pitfalls.75 minutesBuildPythonFree lesson
  13. 13Question Answering SystemsThree systems shaped modern QA. Extractive found spans. Retrieval-augmented grounded them in documents. Generative produced answers. Every modern AI assistant is a mix of the three.75 minutesBuildPythonFree lesson
  14. 14Information Retrieval and SearchBM25 is precise but brittle. Dense casts a wide net but misses keywords. Hybrid is the 2026 default. Everything else is tuning.75 minutesBuildPythonFree lesson
  15. 15Topic Modeling, LDA and BERTopicLDA: documents are mixtures of topics, topics are distributions over words. BERTopic: documents cluster in embedding space, clusters are topics. Same goal, different decompositions.45 minutesLearnPythonFree lesson
  16. 16Text Generation Before Transformers, N-gram Language ModelsIf a word is surprising, the model is bad. Perplexity makes surprise a number. Smoothing keeps it finite.45 minutesBuildPythonMembers
  17. 17Chatbots, Rule-Based to Neural to LLM AgentsELIZA replied with pattern matches. DialogFlow mapped intents. GPT answered from weights. Claude runs tools and verifies. Each era solved the previous one's worst failure.75 minutesLearnPythonMembers
  18. 18Multilingual NLPOne model, 100+ languages, zero training data for most of them. Cross-lingual transfer is the practical miracle of the 2020s.45 minutesLearnPythonMembers
  19. 19Subword Tokenization, BPE, WordPiece, Unigram, SentencePieceWord tokenizers choke on unseen words. Character tokenizers blow up sequence length. Subword tokenizers split the difference. Every modern LLM ships on one.60 minutesLearnPythonMembers
  20. 20Structured Outputs & Constrained DecodingAsk an LLM for JSON. Get JSON most of the time. In production, "most" is the problem. Constrained decoding turns "most" into "always" by editing the logits before sampling.60 minutesBuildPythonMembers
  21. 21Natural Language Inference, Textual Entailment"t entails h" means a human reading t would conclude h is true. NLI is the task of predicting entailment / contradiction / neutral. Boring on the surface, load-bearing in production.60 minutesLearnPythonMembers
  22. 22Embedding Models, The 2026 Deep DiveWord2Vec gave you a vector per word. Modern embedding models give you a vector per passage, cross-lingual, with sparse, dense, and multi-vector views, sized to fit your index. Pick wrong and your RAG retrieves the wrong thing.60 minutesLearnPythonMembers
  23. 23Chunking Strategies for RAGChunking configuration influences retrieval quality as much as the choice of embedding model (Vectara NAACL 2025). Get chunking wrong and no amount of reranking saves you.60 minutesBuildPythonMembers
  24. 24Coreference Resolution"She called him. He did not answer. The doctor was at lunch." Three references to two people and nobody is named. Coreference resolution figures out who is who.60 minutesLearnPythonMembers
  25. 25Entity Linking & DisambiguationNER found "Paris." Entity linking decides: Paris, France? Paris Hilton? Paris, Texas? Paris (the Trojan prince)? Without linking, your knowledge graph stays ambiguous.60 minutesBuildPythonMembers
  26. 26Relation Extraction & Knowledge Graph ConstructionNER found the entities. Entity linking anchored them. Relation extraction finds the edges between them. A knowledge graph is the sum of nodes, edges, and their provenance.60 minutesBuildPythonMembers
  27. 27LLM Evaluation, RAGAS, DeepEval, G-EvalExact-match and F1 miss semantic equivalence. Human review does not scale. LLM-as-judge is the production answer, with enough calibration to trust the number.75 minutesBuildPythonMembers
  28. 28Long-Context Evaluation, NIAH, RULER, LongBench, MRCRGemini 3 Pro advertises 10M tokens of context. At 1M tokens, 8-needle MRCR drops to 26.3%. Advertised ≠ usable. Long-context evaluation tells you the actual capacity of the model you are shipping on.60 minutesLearnPythonMembers
  29. 29Dialogue State Tracking"I want a cheap restaurant in the north... actually make it moderate... and add Italian." Three turns, three state updates. DST keeps the slot-value dict in sync so the booking works.75 minutesBuildPythonMembers
Next phase: Speech & Audio →