Department of Computer Science
Middlebury College
CS 457 - Natural Language Processing
Fall 2011

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: Bicentennial Hall 635
  M/W 2:45-3:45pm
  T 2-3pm
  Th 3-4pm
  and by appointment

time: T/Th 11am-12:15
location: Bicentennial Hall 632
web page:


Other information:



Note: This is a tentative schedule and will likely change  
9/13introduction (ppt)Ch 1, articleAssignment 0
Due Thursday
9/15corpus analysis (ppt)Ch 2.1Assignment 1Cleverbot Article
9/20probability (ppt)Ch 3.1, 3.8-3.13  
9/22language modeling (ppt)Ch 4.1-4.4, article  
9/27language modeling (ppt)
discounting handout
Ch 4.5-4.12Assignment 2 
9/29lm lab   
10/4syntax basics (ppt)Ch 5-5.3, 12.1-12.2 Quiz 1
10/6grammars, parsing (ppt)Ch 13-13.4Assignment 3 
10/11parsing (ppt)Ch 14-14.4, article  
10/13parsing (better models) (ppt)Ch 14.5-14.11  
10/18parsing lab
 Assignment 4 
10/20text similarity (ppt)Ch 20.6-20.8 Quiz 2
10/25NO CLASS   
10/27word similarity (ppt)
11/1ML basics, regression (ppt)Ch 6.6Assignment 5 
11/3logistic regression (ppt)Ch 6.7, article  
11/8unsupervised learning (ppt) Final project 
11/10ML lab   
11/15uninformed search (ppt)  Quiz 3
11/17informed search (ppt)   
11/22MT (ppt)Ch 25-25.4  
11/24NO CLASS   
11/29information retrieval (ppt)IR Ch 1  
12/1MT lab slides (ppt)   
12/6information extraction (ppt)Ch 22-22.2  
12/8presentation guide (ppt)Ch 23.3-23.6 Quiz 4

We will have final presentations in our final exam slot on Friday, December 16 from 7-10pm.