Schedule
The course schedule may be subject to change.
Dates and Deadlines
Three types of dates are listed on the schedule.
BU Deadlines Important dates from the BU academic calendar
Assignment Released On Blackboard
Assignment Due On Mondays at 9:00 AM unless stated otherwise
Schedule
Weeks 1–2
Corpus Analysis
We learn how to use the Natural Language Toolkit (NLTK) to compare different text corpora in terms of their statistical characteristics.
- Reading
- Textbook Chapter 1
- 9/2
- No lab (first day of class)
- 9/7
- Holiday No class (Labor Day)
Weeks 3–4
NLTK Corpora and Lexical Resources
We learn how to work with corpora and other resources in NLTK, and try some more advanced programming.
- Reading
- Textbook Chapter 2
- 9/14
- HW 1 Released
- 9/16
- BU Deadline Last day to add courses
Weeks 5–7
Strings, Text, and Markup
We learn how orthographic characters, text documents, and text formatting are represented in computers.
- Reading
- Textbook Chapters 3 and 4
- 9/28
- HW 1 due
- 10/7
- BU Deadline Last day to drop courses (without a “W” grade)
- 10/12
- Class will be held on 10/13 instead (Indigenous People’s Day)
- HW 2 released
Weeks 8–10
Tagging and Language Modeling
We learn our first “real” NLP tasks: tagging and language modeling (also known as next token prediction).
- Reading
- Textbook Chapter 5
- 10/26
- HW 2 due
- 10/26–10/30
- No class (Sophie is at a conference)
Weeks 11–12
Text Classification
We learn about text classification, the task of assigning a text document one of several pre-defined labels.
Weeks 13–15
Study Period
Final Exam Week
- 12/14
- Final Project Released
- 12/18
- Final Project Due at 11:59 PM