CSE 8803 · Spring 2026

Applied NLP Study Guide

Your interactive learning companion for Weeks 1–10. Built from slides, transcripts, and real quiz patterns — with visuals, demos, and quiz prep.

📅 Current: Week 10 (Mar 16–20) 📚 12 Weeks Covered 🎯 Quiz 9 due Apr 3 — Quiz 10 covers Week 12
Week 12 of 16 — 75% through the course
📚 Weekly Study Notes
Week 1 · Jan 12–16

Intro & Text Preprocessing

Modules 1 & 2 — Foundational NLP
  • Course overview & NLP problem types
  • Tokenization, stemming, lemmatization
  • Stop words, N-grams, noise removal
  • One-Hot Encoding, Bag of Words (BoW)
  • TF-IDF importance weighting
HW1 starts here Open →
Week 2 · Jan 19–23

Naïve Bayes & Classification Evaluation

Module 3 — First Classifier
  • Bayes’ Rule: Prior, Likelihood, Posterior
  • Generative vs. Discriminative models
  • Multinomial Naïve Bayes for NLP
  • Confusion Matrix, Precision, Recall, F1
  • ROC Curve & AUC — MLK Day holiday (Jan 20)
HW1 covers this Open →
Week 3 · Jan 26–30

Logistic Regression, SVM & Perceptron

Module 4 — Linear Classifiers
  • Sigmoid function & soft classification
  • Gradient descent & MLE
  • Support Vector Machines & margin
  • Kernel trick (non-linear SVM)
  • Perceptron algorithm & convergence
HW2 starts here Open →
Week 4 · Feb 2–6

SVD, Co-occurrence & GloVe

Module 5 — Word Embeddings I
  • Why dimensionality reduction?
  • Co-occurrence matrix construction
  • Singular Value Decomposition (SVD)
  • Dense word embeddings from SVD
  • GloVe: global co-occurrence + semantics
HW2 covers this Open →
Week 5 · Feb 9–13

Neural Networks & Word2Vec

Module 6 — Deep Learning Intro
  • Activation functions: ReLU, Sigmoid, Tanh
  • Forward pass & Backpropagation
  • Stochastic & Batch Gradient Descent
  • Word2Vec: CBoW model
  • Word2Vec: Skip-Gram model
HW3 starts here Open →
Week 6 · Feb 16–20

Convolutional & Recurrent Neural Networks

Module 7 — Sequence & Structure
  • CNN: filters, convolution, feature maps
  • Max pooling & parameter sharing
  • CNN for text classification
  • RNN: sequential memory & hidden state
  • Vanishing gradient & exploding gradient
HW3 covers this ✓ Open →
Week 7 · Feb 23–Mar 1

LSTM, GRU & Attention

Module 8 — Long-Term Memory & Focus
  • LSTM: cell state, forget / input / output gates
  • Cell state update: C_t = f_t⊙C_{t-1} + i_t⊙C̃_t
  • GRU: 2-gate simplified LSTM
  • Encoder-Decoder architecture
  • Additive Attention (Bahdanau): α weights + C_t
HW4 covers this Open →
Week 9 · Mar 9–13

Transformers, BERT & GPT

Module 9 — The Architecture That Changed NLP
  • Why Transformers? LSTM limitations & pre-training benefits
  • Encoder vs. Decoder: BERT, GPT, T5/BART families
  • Self-Attention: Q, K, V — Attention(Q,K,V) = softmax(QKᵀ/√d_k)·V
  • Positional Encoding: sine (even) / cosine (odd) indices
  • BERT: MLM + NSP pre-training; GPT: autoregressive generation
HW4 · Quiz 8 covers this Open →
Week 10 · Mar 16–20

Sequence Labeling: POS Tagging & NER

Module 10 — Token-Level Classification
  • Sequence labeling: one label per token (input = output length)
  • POS Tagging: Penn Treebank tagset, lexical ambiguity, perceptron & BERT
  • NER: 9 entity types, IOB/BIO tagging — B-PER, I-ORG, O
  • NLTK binary=True/False, Keras transformer, BERT (dslim)
  • Why encoder-only (BERT) is preferred for NER/POS over encoder-decoder
HW4 · Quiz 9 covers this Open →
Week 11 · Mar 23–27

🌴 Spring Break

No lectures · No quiz · Recharge!
No new content this week. Week 12 resumes with Unsupervised Models & Topic Modeling.
No content
Week 12 · Mar 30–Apr 3 ← YOU ARE HERE

Topic Modeling: LSI & LDA

Module 11 — Unsupervised Learning
  • Topic modeling: unsupervised extraction of hidden topics from documents
  • LSI: SVD decomposition A = U × Σ × V¹ — concept matrices
  • LSI querying: map term to concept space using V¹ matrix
  • LDA: Dirichlet distributions for doc-topic (α) and topic-word (β)
  • LDA equation: 4 probability terms — Dirichlet + Multinomial distributions
  • Gibbs sampling optimization for LDA parameter tuning
HW5 out · Quiz 10 covers this Open →
📅 Quiz Schedule & Coverage

All 12 Quizzes — Week Coverage & Dates

QuizCovers WeekTopicDueStatus
Quiz 1Week 1Text Preprocessing & RepresentationsJan 23✓ Done
Quiz 2Week 2Naïve Bayes & ClassificationJan 30✓ Done
Quiz 3Week 3Logistic Regression, SVM & PerceptronFeb 6✓ Done
Quiz 4Week 4SVD, Co-occurrence & GloVeFeb 13✓ Done
Quiz 5Week 5Neural Networks & Word2VecFeb 20✓ Done
Quiz 6Week 6CNN & RNNFeb 27✓ Done
Quiz 7Week 7LSTM, GRU & AttentionMar 6✓ Done
Quiz 8Week 9Transformers, BERT & GPTMar 20✓ Done
Quiz 9Week 10POS Tagging & NERApr 3⚠ Due Apr 3!
Quiz 10Week 12Topic Modeling: LSI & LDAApr 10▶ Upcoming
Quiz 11Week 13LLMs & Prompt EngineeringApr 24— Future
Quiz 12Week 14AI Agents & ApplicationsMay 1— Future
🗺️ Course Learning Roadmap
From raw text → intelligent models
Raw Text
→
Preprocessing
W1
→
Representations
W1
→
Classifiers
W2–W3
→
Embeddings
W4–W5
→
Deep Models
W5–W6
→
Transformers
W9
→
Seq. Labeling
W10
→
LLMs / Agents
W13–W14
💡 How to Use These Notes
🧠

What → Why → How

Every concept is explained in three layers: what it is, why we need it, and how it works mechanically. Read all three before moving on.

🎮

Use the Interactive Demos

Each week has live visualizers and clickable demos. Change the inputs and watch outputs update — this is the fastest way to build intuition.

📝

Quiz Yourself

Each week ends with multiple-choice questions modeled after actual Quizzes 1–7. Cover the answer, try it yourself, then reveal. Repeat weak spots.

🔗

Follow the Thread

Each week builds on the last. If something in Week 9 is confusing, check Week 7 (LSTMs). The roadmap above shows exactly how concepts connect.