Department of Computer Science
Pomona College
CS 159 - Natural Language Processing
Spring 2023

instructor: Dave Kauchak
e-mail: David.[last_name]@pomona.edu
office hours: Edmunds 224
  Tue, Thu - 9:30-11am
  Fri - 9 - 10am
  and by appointment

mentor hours: Sam: Thu - 7-9pm (Edmunds upstairs)

time: M/W 1:15-2:30pm
location: Edmunds 101
web page: http://www.cs.pomona.edu/classes/cs159/

textbook:

Other information:

Schedule

Note: This is a tentative schedule and will likely change
DateTopicReadingAssignmentOther
1/18 introduction (ppt) Ch. 1 Assignment 0 Due: Friday 1/20 @ 5pm
1/23 regular expressions (ppt), corpus analysis (ppt) Ch. 2-2.4 Assignment 1 Due: Monday 1/30 @ 1pm
1/25 probability (ppt)  
1/30 language modeling (ppt) Ch. 3-3.4 Assignment 2a (solution) - 2b A Due: Friday 2/3 @ 5pm
B Due: Friday 2/10 @ 5pm
2/1 LM smoothing (ppt)
discount example
Ch. 3.4-3.6
2/6 LM lab
2/8 syntax basics (ppt) Ch. 17-17.3 Assignment 3 Due: Monday 2/20 @ 1pm
2/13 grammars ppt Quiz 1
2/15 parsing (ppt) Ch. 17.4-17.6
2/20 improved parsing (ppt) Ch. 17.8 Assignment 4a (solution) - 4b A Due: Wednesday 2/22 @ 1pm
B Due: Friday 3/3 @ 5pm
2/22 parsing lab
2/27 text similarity (ppt) Ch. 6-6.7
3/1 word similarity (ppt)
3/6 neural networks (ppt) Ch. 7-7.4 Assignment 5 (5a solutions) A Due: Friday 3/10 @ 5pm
B Due: Monday 3/27 @ 1pm
3/8 Quiz only Quiz 2
3/13 Break
3/15 Break
3/20 word representations (ppt) Ch. 6.8-6.11
3/22 machine translation (ppt) Ch. 13-13.2
3/27 MT - word alignment (ppt) Assignment 6 Due: Friday 4/7 @ 5pm
3/29 MT - misc (ppt)
4/3 machine learning (ppt)
4/5 ML - Naive Bayes (ppt) Ch. 4-4.3
4/10 final project details Quiz 3
4/12 ML - other models (ppt) Assignment 7 Due: Monday 4/17 @ 5pm
4/17 ML lab, project proposal presentations final project
4/19 large language models (ppt) watch before class, Ch. 9
4/24 text simplification (ppt)
4/26 ethics discussion LLMs (full article), profiling, data use
5/1 presentation guide Quiz 4
5/3 project presentations
Other topics we'll likely cover: