Homeworks

• HW0: due Friday, Sept 8, on Gradescope. (If you like: hw0.tex source)
  • Resources: for probability/math basics, some people like the mathematicalmonk youtube channel; the prob. primer section has some relevant ones, like PP 2.1-2.5, 3.1-3.3.
• HW1: due at 11PM on Friday, Sept 22, on Gradescope. You will need to download two files hw_1.py and hw_1.ipynb. You will also need to download the data file, which is around 46 MB to download, and takes around 210 MB when unzipped. (For reference: html format)
• HW2: due at 11pm on Tuesday, Oct 10. (For reference: html format)
• HW3: due at 11pm on Friday, Nov 11. Download hw3.zip (26 MB). (For reference: see html format)
• HW4: due at 11pm on Friday, Dec 15. Download hw4.zip. (For reference: see html format)

Schedule

Make sure to reload this page to ensure you’re seeing the latest version. Readings should be done before the indicated class. Texts include:

• JM = Jurafsky and Martin, Speech and Language Processing, 3rd edition draft chapters
• Eis. = Eisenstein draft text

Tue 9/5 - Introduction [slides]

Thu 9/7 - Words [slides]

• Reading: JM 2.1-2.3 (from the "Regex, Text Normalization, Edit Dist" chapter)
• See also: "Unix for Poets" by Ken Church
• Python demo from lecture

Tue 9/12 - N-Gram Language Models [slides]

• Reading: JM 4.1-4.4
• In-class exercise: Shannon game

Thu 9/14 - Classification: Naive Bayes [slides]

• Reading: JM 6.1-6.5
• Optional: Eis., ch. 1

Tue 9/19 - Classification: Evaluation and Annotation [slides], [scan]

• JM 6.6-6.9
• Eis., 3.5, "Building Datasets"
• Start log-linear models (below)

Thu 9/21 - Classification: Logistic regression [slides]

• In our class we'll use this perspective: logistic regression is a probabilistic model for classification. The perceptron algorithm is one way to learn its parameters from labeled training data. (Maximum likelihood, like we saw for LMs, NB and will for HMMs, is a different learning method.)
• JM ch. 7, Logistic Regression
• Daume ch. 3, The Perceptron

Tue 9/26 - Sequence Tagging: POS and HMMs [announcements] [POS slides] [HMM scan]

• JM 10.1-10.3, Part-of-speech tags
• JM 9.1-9.3, Hidden Markov Models

Thu 9/28 - Sequence Tagging: Viterbi [scan]

• Viterbi/Forward handout
• HMM and Viterbi notes
• JM 9.4 (Viterbi) and JM 10.4 (HMM Part-of-Speech Tagging)

Tue 10/3 - Project Discussion [slides]

Tue 10/3 - Log-linear Perceptron [slides]

• Daume chapter on the perceptron (above) - esp. averaged perceptron.
• Eisenstein text, 6.5, "Discriminative sequence labeling" up to 6.5.1, "Structured Perceptron." Read earlier sections in ch. 6 as necessary.
• From 10/4 office hours: NB as log-linear

Thu 10/5 - Conditional Random Fields [slides]

• CRF example
• Eisenstein text, 6.5.3, "Conditional Random Fields"
• Optional: Eisenstein text, ch. 7, "Applications of sequence labeling"
• Optional: Chen (2012)'s blogpost on CRFs (unfortunately its equations look broken).

Tue 10/10 - No Class

Thu 10/12 - Project proposal info [slides]

• Example proposal

Tue 10/17 - WordNet [slides]

• JM Ch. 17, "Computing with word senses" (WordNet and WSD)

Thu 10/19 - Sentiment lexicons [slides]

• JM Ch. 18, "Lexicons for Sentiment and Affect Extraction"

Tue 10/24 - Midterm review [scan]

• Practice midterm questions

Thu 10/26 - Midterm

Tue 10/31, Thu 11/2 - Distributional Semantics [slides]

• JM Ch. 15, "Vector semantics"
• JM Ch. 16, "Semantics with dense vectors"

Tue 11/7 (cancelled)

Thu 11/9 - Unlabeled data in NLP [slides]

Tue 11/14 - Syntax, phrase structures I [slides]

• Ch. 3 from Manning and Schuetze (1999): "Linguistic Essentials."
• Eisenstein text, 8.2, Context-free languages
• Optional: JM Ch. 11, Formal grammars of English
• Handout: CFG exercise

Thu 11/16 - Syntax, phrase structures II [slides]

• Eisenstein text, 9.1-9.3, Context-free parsing
• Optional: JM Ch. 12, Syntactic parsing

Thanksgiving break - no class

Tue [11/28](18-deps), 11/30 - Dependency Syntax

• JM 14.1-14.4
• Optional: Eisesntein text, Ch. 10, Dependency parsing

Tue 12/5 - Coreference

Thu 12/7 - Generation: Translation and Summarization

Tue 12/12 - Poster session

3:30-6:30pm in CS room 150/151! Divided into two sessions: 3:30-5 and 5-6:30. See information on Piazza.