This schedule is subject to change.

Assignments are due right before class (11am) on their due date unless noted otherwise.

Readings can be done either before or after class (unless noted otherwise); they are chosen to support the material covered in class.

Week 1: Using rules to analyze individual words

• Jan 16: Class canceled because of inclement weather
  
  
• Jan 18: Introduction, and a demo of some computational linguistics tasks and methods.
• The demo is here.

Week 2

• Jan 23: Introduction to programming: Python basics
  • Worksheet: first steps in Python.
• Reading: Think Python chapter 1 and chapter 2
  Warning: This online book uses Python 2, not Python 3. The main difference that you will see is that it uses print() without the (). This doesn't work in Python 3!
  
  
• Jan 25: Introduction to programming: Writing functions in Python
  • Worksheet: Building your own Python functions
• Readings: Think Python chapter 3, chapter 5

Week 3

• Jan 30: Morphology, finite state automata and finite state transducers
• Taking words apart: What do "sing", "singing", "sings", "sang" have in common, and how do we describe what is different?
• Reading: J&M ch. 2 second half, ch. 3, pp. 45-68
• Assignment 1 due
  
  

• Feb 1: Introduction to programming: Python conditions and lists
  
• Worksheet: Python conditions, lists, and loops
  
• Reading: Think Python chapter 4

Week 4

• Feb 6: Finite state transducers, and regular expressions
• Python worksheet: regular expressions
• A guide to regular expressions in Python, also Regular expressions with many examples, from "Dive into Python", and a regular expressions primer.
  

• Feb 8: Introduction to programming: Writing more complex programs: Python loops. Also: file handling
  
• Continuing on Worksheet: Python conditions, lists, and loops.
• Worksheet: Reading and writing files in Python
• Python list comprehensions
• Reading: Think Python chapter 6 and chapter 12

Week 5

• Feb 13: Finishing up regular expressions and finite state automata.
  Then: Using rules to write natural language processing systems: Dialog systems
  
• Eliza and Parry examples, another Eliza example
  
• Implementing Eliza
• Assignment 2 due

• Feb 15: Introduction to programming: Counting words with Python dictionaries and with the Natural Language Toolkit
• Worksheet: Python dictionaries
• Worksheet: Sorting in Python
• Using Python dictionaries: mapping strings to lists
• The nltk.FreqDist data type is described in chapter 1 of the NLTK book.

Week 6

• Feb 20: Machine learning. Method: Naive Bayes classifiers. Application: Sentiment analysis.
  
• Demo: conditional probability
• Reading: J&M edition 3, chapter 6 (available online by this link)
• In class: course project discussion. Bring your ideas!
  

• Feb 22: Typical word sequences: Language models
• Methods: Probabilistic approaches, n-grams
• Reading: J&M ch. 4, pp 83-97
• Demo: Language models in Python
• Assignment 3 due

Week 7

• Feb 27: Language models continued
  

• Mar 1: Is this a noun or a verb? Part-of-speech tagging.
• Readings: NLTK book chapter 5 section 4; 
  J&M ch. 2 first half
• Assignment 4 due

Week 8: Word sequences

• Mar 6: Guest lecture: Jessy Li on discourse structure analysis
  

• Mar 8: Sequence information in Part-of-speech tagging
  
• Methods: Hidden Markov Models (HMMs), dynamic programming
  
• Reading: J&M ch. 5 pp. 139-149, ch. 6 pp. 173-179, NLTK book ch. 5 sec. 5.5
  
• Hidden Markov Models for POS-tagging in Python
• Assignment 5 due
  

Week 9: Spring break

Week 10

• Mar 20: Training HMMs
• Method: Expectation Maximization
  
• Demo: the forward-backward algorithm

• Mar 22: More HMMs
• Intermediate project report due
  

Week 11: Structure

• Mar 27: Chunking and parsing
  
• Reading: NLTK book ch. 7, sec. 7.2 and 7.3
• Reading: J&M ch.12, pp. 385-404

• Mar 29: Describing the syntax of English with context-free grammars
• Method: Context-free grammar
• Assignment 6 due
  
  

Week 12

• April 3: Automatic syntactic analysis: Parsing
• Reading: J&M ch. 13, pp. 427-450, NLTK book ch. 8
• Links for course projects:
  
• check the NLTK chapter on classification, chapter 6.
• a Python machine learning package: scikit-learn
  
• On error analysis, check Emily Bender's blog post on "putting the linguistics in computational linguistics"
  

• April 5: Statistical parsing
• Method: Probabilistic context-free grammar
  
• Reading: J&M ch. 14 pp. 459-463, 467
• Here is a phrase structure parser that you can try out. It uses the LinGO English Resource Grammar.
  If you would like to see a sentence with PP attachment issues, try: "We quickly put up the tents in the lee of a small hillside and cook for the first time in the open."
• Assignment 7 due

Week 13

• April 10:  The Chomsky hierarchy, or: how complex is human language?
• Reading: J&M, ch. 16, pp 529-542

• April 12:  Automatically determining word meaning: Distributional models
• Reading: J&M 3rd ed., chapter 15, available online via this link
• Slides
  
• Some ready-made distributional models you can use for your project, if needed: scroll down to "Where to get a pretrained model"
  
• Assignment 8 due

Week 14

• April 17: More distributional models

• April 19: Representing sentence meaning

Week 15

• April 24: Applications: Machine Translation
• Reading: J&M ch. 25, p. 859-876
• Material:  Koehn and Callison-Burch ESSLLI slides, more slides