Schedule subject to change.

All assignments are due at the end of the day that is the due date.

Aug 28: Introduction to working with corpora and programming in Python

•     Slides
  

Sep 2: Using programming to explore corpora -- a lightning tour. We use chapter 1 of the NLTK book.

Sep 4: Python basics.

• Worksheet: First steps in Python
  

• Readings: NLTK chapter 1 section 1.1 only.   Think Python chapter 1 and chapter 2 (Read this after class.)

Sep 9: What corpora are available? Some examples, and uses

• Readings: NLTK chapter 2

Sep 11: Strings and functions in Python

• Worksheet: Building your own Python functions
• Readings: Think Python chapter 7 (strings), 
  Think Python chapter 3 (functions), 5 (fruitful functions),

Week 4

Week 5

Sep 23: Text formats and text encoding

• Python worksheet: accessing and processing text
  
• Readings: NLTK chapter 3

Sep 25:Python list comprehensions

• Here are some more List and loop problems
• Worksheet: Python list comprehensions

Sep 30:Making corpora

• Readings NLTK chapter 11
• Slides: slides on making corpora
  
• Related reading:
  
• Bird and Simons (2003): Seven Dimensions of Portability for Language Documentation and Description

Oct 2:Annotating corpora: formats

• Slides on annotation formats
  
• Readings: Wynne chapters 1 and 2

Week 7

Oct 7: Annotating corpora: quality control

• Slides: Annotation quality
• Assignment 2 due

Oct 9: Sample Python programs

• Sample Python programs here
  
• We also talk in class about your project ideas.

Oct 14: Guest lecture

Oct 16: Guest lecture

Oct 21: Python dictionaries

• Worksheet: Python dictionaries
  
• Readings: Think Python chapter 11 (dictionaries), NLTK chapter 1  sec. 1.3
• Project proposal due. Information on format and contents are available on the Working with Corpora: Assignments page.

Oct 23: Regular expressions

• Slides
  
• Readings: A guide to regular expressions in Python, also Regular expressions with many examples, from "Dive into Python", and a regular expressions primer.

Oct 28: Regular expressions continued

• Assignment 3 due

Oct 30: Searching annotated corpora

• Slides: searching annotated corpora
  
• We make use of the Opus Europarl interface at http://opus.lingfil.uu.se/cwb/Europarl/frames-cqp.html
• We use tregex, available at http://nlp.stanford.edu/software/tregex.shtml#Download
  

Nov 4: Searching annotated corpora, continued.

Nov 6: Automatic analysis of text with the Natural Language Toolkit

• Readings: NLTK ch. 5 starting at section 4, and NLTK ch. 7 section 7.2.
• NLTK demo code
  

Nov 11: Sample programs for text analysis.

• Project presentation: Rebecca Kurlak
  
• Python code snippets
• Project progress report due

Nov 13: A glimpse at the R statistics package.

• Here is the download link for the R statistics package
• Worksheet: First steps in R
• Some data computed from the NLTK Inaugural speech corpus: Word counts in inaugural speeches

Nov 18: A very short introduction to some concepts from statistics.

• Harald Baayen's Analyzing Linguistic Data
• Assignment 4 due
• Additional material we may use: Data exploration, Fisher telephone conversation corpus: table 1, table 2
• Extra questions about the Inaugural data:
• What was the longest speech in the 19th century? (Give the year, the president's name, and the length of the speech.) What was the longest speech in the 20th century?
•  Who used "I" the most? (That is, what is the name of the president who used "I" the most.) Who used "I" and "me" combined the most?
•  How many speeches used the term "freedom" at least 5 times?
•  How many speeches that used the term "freedom" at least 5 times were later than 1980?
•  How long is the longest name of a president? (nchar() gives you the length of a string, and remember to use as.character() to convert from factor to string.)
•  DIFFICULT: How many presidents served twice? (For this you need to use the code from the worksheet that adds in the name of the previous president.)
• Worksheet
  

Nov 20: A very short introduction to some concepts from statistics, continued

Nov 25: A very short introduction to some concepts from statistics, continued.

Dec 2: Project presentations 

• 12:30 Hoyoung Yi
• 12:42 Adam McBride
• 12:55 Rozen Neupane
• 13:07 Maxim Baryshevtsev
• 13:20 Whitman Suarez
• 13:32 Liang Sun

Dec 4: Project presentations

• 12:30 Viola Green
• 12:42 Ethan Cooper
• 12:55 Margo Blevins
• 13:07 Magdalena Saldana
• 13:20 Saif Shahin
• 13:32 Shannon McGregor
• 13:45 Patrick Schultz
  

Final report due: Monday December 8, end of the day