Original Academy
Legacy mirror · noindex · upstream phase 5
NLP: Foundations to Advanced
Language is the interface to intelligence.
Provenance: this phase outline and its lesson readings are preserved from ai-engineering-from-scratch by Rohit Ghumare under the MIT License. InterviewsVector does not claim authorship. These archive pages remain available for old links and progress, but are excluded from indexing.
Attributed readings
- 01Text Processing: Tokenization, Stemming, LemmatizationLanguage is continuous. Models are discrete. Preprocessing is the bridge.
- 02Bag of Words, TF-IDF & Text RepresentationCount first, think later. TF-IDF still beats embeddings on well-defined tasks in 2026.
- 03Word Embeddings: Word2Vec from ScratchA word is the company it keeps. Train a shallow net on that idea and geometry falls out.
- 04GloVe, FastText & Subword EmbeddingsWord2Vec trained one embedding per word. GloVe factorized the co-occurrence matrix. FastText embedded the pieces. BPE bridged to transformers.
- 05Sentiment AnalysisThe canonical NLP task. Most of what you need to know about classical text classification shows up here.
- 06Named Entity Recognition (NER)Pull the names out. Sounds easy until you deal with ambiguous boundaries, nested entities, and domain jargon.
- 07POS Tagging & Syntactic ParsingGrammar was unfashionable for a while. Then every LLM pipeline needed to validate structured extraction, and it came back.
- 08Text Classification — CNNs & RNNs for TextConvolutions learn n-grams. Recurrences remember. Both are superseded by attention. Both still matter on constrained hardware.
- 09Sequence-to-Sequence ModelsTwo RNNs pretending to be a translator. The bottleneck they hit is the reason attention exists.
- 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.
- 11Machine TranslationTranslation is the task that paid for NLP research for thirty years and keeps paying now.
- 12Text SummarizationExtractive systems tell you what the document said. Abstractive systems tell you what the author meant. Different tasks, different pitfalls.
- 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 th…
- 14Information Retrieval & SearchBM25 is precise but brittle. Dense casts a wide net but misses keywords. Hybrid is the 2026 default. Everything else is tuning.
- 15Topic Modeling: LDA, BERTopicLDA: documents are mixtures of topics, topics are distributions over words. BERTopic: documents cluster in embedding space, clusters are topics. Same goal, different decompositi…
- 16Text GenerationIf a word is surprising, the model is bad. Perplexity makes surprise a number. Smoothing keeps it finite.
- 17Chatbots: Rule-Based to NeuralELIZA 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.
- 18Multilingual NLPOne model, 100+ languages, zero training data for most of them. Cross-lingual transfer is the practical miracle of the 2020s.
- 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.
- 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.
- 21NLI & 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 produc…
- 22Embedding Models 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. P…
- 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.
- 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.
- 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.
- 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.
- 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.
- 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 mode…
- 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 …