Computer Science 394

Seminar: Computational Linguistics
Fall 2013
Thomas VanDrunen



Meeting time: Th 8:30-10:20 am.
Meeting place: Science 131

Office hours: MWThF 3:15-4:45 pm; Th 11:00 am--12:00 noon.
Contact: Sci 163 ; 752-5692; Thomas.VanDrunen@wheaton.edu
http://csnew.wheaton.edu/~tvandrun/cs394


Syllabus




Final exam: Thursday, Dec 19, 8:00 AM

Moon's dayWoden's dayThor's dayFrigga's day

Aug 26

Aug 28

Aug 29

Introduction
Slides

Read JM chapter 1; section 2.1; section 3.1

Aug 30

Sept 2

NO CLASS

Sept 4

Sept 5

Introduction to NLTK; Regular expressions.

Sept 6

Sept 9

Sept 11

Sept 12

Probability and statistics background

Homework problems
Read JM 3.1, 4.(1-3)

Sept 13

Project 1, Due Oct 3

Sept 16

Sept 18

Sept 19

Language models; n-grams
Slide

Read JM 4.(4 & 5)

Sept 20

Sept 23

Sept 25

Sept 26

Other things about n-grams
Handout

Read JM 4.(4 & 5) (if you haven't yet)

Sept 27

Sept 30

Oct 2

Oct 3

Good-Turing and other smoothing
Slides

Read JM 3.(10 & 11), 5.9

Oct 4

Oct 7

Oct 9

Oct 10

Edit distance

Read JM 4.10

Oct 11

Project 2, due Nov 6

Oct 14

Oct 16

Oct 17

Information theory
Slides

Oct 18

Oct 21

NO CLASS

Oct 23

Oct 24

The entropy of English
Slides

Read JM chapter 5 through page 145

Oct 25

Oct 28

Oct 30

Oct 31

Lexical categories; introduction to Hidden Markov Models
Slides

Review last week's reading and read JM 5.5.3

Nov 1

Nov 4

Nov 6

Nov 7

HMMs; POS tagging

Project 3, due Dec 4
Rread JM chapter 19

Nov 8

Nov 11

Nov 13

Nov 14

Lexical semantics
Lab activity

Read JM sections 12.1&2 carefully. Skim sections 12.(3&4) and chapter 13 through 13.4.1.

Nov 15

Nov 18

Nov 20

Nov 21

A closer look at dynamic programming; revisiting edit distance and the Viterbi algorithm

Nov 22

Nov 25

Nov 27

NO CLASS

Nov 28

NO CLASS

Nov 29

NO CLASS

Dec 2

Dec 4

Dec 5

Generative grammars and parsing

Project 4, due Friday, Dec 13

Dec 6

Dec 9

Dec 11

Dec 12

Authorship attribution

Dec 13