W  Date 
Lecture 
Lab 
Assignment (due next class) 

1  8/27 (T) 
Intro to CL 
Setup, orientation, string processing 
Exercise 1: Python refresher quiz 
8/29 (Th) 

Python functions, data types 
Exercise 2: Python quiz, Pig Latin 

2  9/3 (T) 
Encoding systems, Unicode 
Text processing with NLTK 
Exercise 3 
9/5 (Th) 
Spell checking fundamentals: edit distance 

HW1: spell checker, text processing 

3  9/10 (T) 
ngram context 
List comprehension 
Ex 
9/12 (Th) 
Conditional probability, ngram frequency 
NLTK's ngram functions, conditional freq dist 
HW2: Bigram Speak 

4  9/17 (T) 
HW2 review; Ngram language models 
Processing web resources 
Ex 
9/19 (Th) 
Corpus linguistics: type, token, TTR 
NLTK's corpus tools 
HW3: corpus processing (weeklong) 

5  9/24 (T) 
Zipf's law, freq distribution, ngrams 

 
9/26 (Th) 
HW3 review 

Ex 

6  10/1 (T) 
Naive Bayes classifier intro 
NLTK's Naive Bayes classifier 
HW4: Who said it? (weeklong) 
10/3 (Th) 
Bayes theorem, evaluation metrics 

 

7  10/8 (T) 
HW4 & midterm review 

 
10/10 (Th) 
Midterm exam 

8  10/15 (T) 
Regex, FSA 

Ex 
10/17 (Th) 


HW5: Python's re module 

9  10/22 (T) 
Morphology, FST 

Ex 
10/24 (Th) 


HW6: morphological analysis 

10  10/29 (T) 
POS tagging 

Ex 
10/31 (Th) 


HW7: POS tagging 

11  11/5 (T) 
Trees, parsing 

Ex 
11/7 (Th) 


HW8: CFG and parsing 

12  11/12 (T) 


Ex 
11/14 (Th) 
Computational semantics: WordNet 

HW9: WordNet and word vectors 

13  11/19 (T) 
Distributed semantics 

 
11/21 (Th) 


HW10: deep learning & MT 

Thanksgiving break (whole week) 

14  12/3 (T) 
Formal language theory 

 
12/5 (Th) 


 

15  Date TBD 
Final exam 
*Class schedule is subject to revision throughout the semester.
