This schedule is tentative and subject to change as the semester progresses.
| Date | Lecture | Reading | Assignment | ||
|---|---|---|---|---|---|
| Introduction, N-grams | |||||
| Th | 1/13 | 1 | What is NLP? | SLP2 ch. 1 | A0: The Basics |
| Tu | 1/18 | 2 | Why do we need data?; Basic Text Processing (Regular Expressions, Normalization) | Working with text in Python 3, SLP3 2.0–2.3, NLTK Book 3.2–3.10 | |
| Th | 1/20 | 3 | N-gram language models | SLP3 3.0–3.4.2; Goldwater probability review through section 4 | A0 due |
| Tu | 1/25 | 4 | N-gram language models contd. | A1: Language Models | |
| Th | 1/27 | 5 | Overview of Linguistics | Features English is missing - but most other languages have; SLP2 1.1, SLP3 10.1 | |
| Classification | |||||
| Tu | 2/1 | 6 | Classification: naïve Bayes; Noisy Channel Model | SLP3 4.0–4.5 | |
| Th | 2/3 | 7 | Lexical semantics: senses, relations, classes | SLP3 18.0-18.3 | |
| Fr | 2/4 | A1 due | |||
| Tu | 2/8 | 8 | Linear models for classification: features & weights | SLP3 5.0–5.2 | A2: Perceptron |
| Th | 2/10 | 9 | Linear models for classification: discriminative learning (perceptron, SVMs, MaxEnt) | Daumé The Perceptron: 4.0–4.3; SLP3 4.7–4.8, ch. 5 (Further readings are suggested in slides) | |
| Tu | 2/15 | 10 | Linear models contd. | ||
| Sequential Prediction | |||||
| Th | 2/17 | 11 | Parts of speech; Review | SLP3 8.0–8.3 | |
| F | 2/18 | A2 due | |||
| Tu | 2/22 | No class: classes follow Monday schedule | |||
| Th | 2/24 | 12 | POS tagging: HMMs | SLP3 8.4.0–8.4.3 Eisenstein Notes, 7.1: Part-of-speech tagging | |
| F | 2/25 | GRADED QUIZ 1 | (See study guide worksheet) | ||
| Tu | 3/1 | 13 | Algorithms for HMMs (mainly Viterbi); BONUS: Discriminative tagging with the structured perceptron | SLP3 8.4.4–8.4.6, Appendix A; BONUS: Eisenstein Notes, 7.5 (no need to read beyond structured perceptron); Neubig slides | |
| Th | 3/3 | 14 | Annotation; Universal POS annotation activity (tagset) | A3: HMM | |
| M-F | 3/7-3/11 | No class or office hours: Spring Break | |||
| Distributed Representations and Neural Networks | |||||
| Tu | 3/15 | 15 | Distributional representations and similarity | SLP3 ch. 6 | |
| Th | 3/17 | 16 | Deep learning and neural networks | SLP3 7.0–7.1, 7.3–7.5 | |
| F | 3/18 | A3 due | |||
| Tu | 3/22 | 17 | Neural sequence modeling with RNNs (Jakob Prange) | SLP3 9.1–9.8 | A4: LSTMs |
| Hierarchical Sentence Structure | |||||
| Th | 3/24 | 18 | English syntax, CFGs | SLP3 12.0–12.3, skim 12.4 | |
| Tu | 3/29 | 19 | Syntax contd.; forming project teams | ||
| Th | 3/31 | 20 | Syntax, CFGs contd. (P)CFG parsing: Parsing as search; CNF. | P0: Submit project team with topic | |
| F | 4/1 | A4 due | |||
| Tu | 4/5 | 21 | (P)CFG parsing contd.: CKY walkthrough | SLP3 13.0–13.2, Appendix C C.0-C.4 | P1: 1-2 page proposal due |
| Th | 4/7 | 22 | (P)CFG parsing contd.: CKY pseudocode, PCFGs, lexicalization | A5: Syntax | |
| Th-F | 4/7-4/8 | P2: groups meet with instructor & TA | |||
| Tu | 4/12 | 23 | Dependency parsing | SLP3 14.0-14.4, 14.6 | |
| Th-M | 4/14-4/18 | No class or office hours: Easter Break | |||
| Tu | 4/19 | 24 | Semantic role labeling | SLP3 15.0, 19.1-19.6 | |
| Translation and Sequence-to-Sequence | |||||
| Th | 4/21 | 25 | Statistical machine translation | SLP3 10.2–10.9 | P3: Progress update, including lit review, due |
| F | 4/22 | GRADED QUIZ 2 | Study guide to appear | ||
| Tu | 4/26 | 26 | Statistical machine translation contd. | ||
| Tu | 4/28 | 27 | Neural sequence-to-sequence models (Luke Gessler) | ||
| F | 4/29 | A5 due | |||
| Tu | 5/3 | 28 | Last day of class; Context in language processing + Wrap-up | ||
| W | 5/11 | VIRTUAL PROJECT POSTER SESSION (12:30-2:30) | |||
| F | 5/13 | PROJECT REPORT DUE | |||
| Visit the GUCL website for NLP talks this semester and beyond! | |||||