Department of Computer Science
Pomona College
CS 159 - Natural Language Processing
Fall 2014

An introduction to fundamental concepts in natural language processing and computational linguistics, a field whose goals include enabling human-computer interaction via language and text translation and understanding. Use of statistical and logical techniques to study language processing at word, synatactic, and semantic levels. Assignments require constructing and modifying systems as well as using large, existing corpora for validation.

instructor: Dave Kauchak
e-mail: [first_initial][last_name]
office hours: Edmunds 224
  Mon. 10:30am-12
  Thu. 11am-12
  Fri. 1:30-3:00pm
  and by appointment

time: T/Th 2:45-4pm
location: SCOM 103 (Seaver Commons)
web page:


Other information:



Note: This is a tentative schedule and will likely change
9/2introduction (ppt)Ch 1, articleAssignment 0 
9/4corpus analysis (ppt)Ch 2.1Assignment 1 
9/9probability (ppt)Ch 3.1, 3.8-3.13  
9/11language modeling (ppt)Ch 4.1-4.4Assignment 2a (solution)
Assignment 2b
9/16lm smoothing (ppt)
discounting handout
Ch 4.5-4.12  
9/18lm lab (Edmunds 105)Javadoc  
9/23syntax basics (ppt)Ch 5-5.3, 12.1-12.2  
9/25grammars (ppt)Ch 13-13.4Assignment 3Quiz 1
9/30parsing (ppt)Ch 14-14.4  
10/2improved parsing (ppt)Ch 14.5-14.11Assingment 4a (solutions)
Assignment 4b
10/7parsing lab (Edmunds 105)   
10/9text similarity (ppt)Ch 20.6-20.8  
10/14word similarity (ppt)   
10/16distributional similarity (ppt) Assignment 5 (solutions)Quiz 2
10/21Fall break  
10/23machine translation (ppt)Ch 25-25.1  
10/28MT - translation models (ppt)Ch 25.3, 25.5  
10/30MT - word alignment (ppt)Ch 25.6
IBM 1-2 (optional)
Assignment 6 
11/4MT conclusions (ppt)Ch 25.4, 25.9  
11/6MT lab (Edmunds 105)   
11/11machine learning (ppt)Daume 1-1.2final project 
11/13ML - NB (ppt)Manning 13.1-13.4Assignment 7 
11/18ML - priors (ppt)  Quiz 3
11/20ML - other models (ppt)   
11/25ML lab (Edmunds 105)   
12/2Text modeling (ppt)   
12/4Text simplification (ppt)   
12/9presentation guide  Quiz 4

We will have final presentations in our final exam slot on Tuesday, December 16 from 2-5pm.