Computer Science 384

Computational Linguistics
Fall 2015
Thomas VanDrunen



Meeting time: MWF 3:15-4:20 pm.
Meeting place: Science 184

Office hours: MTuWThF 9:15-10:15 am; Th 1:30-3:30 pm.
Contact: 163 Science; 752-5692; Thomas.VanDrunen@wheaton.edu
http://cs.wheaton.edu/~tvandrun/cs384


Syllabus
How to do reading assignments

Resources on Hidden Markov Models:
"A Revealing Introduction to Hidden Markov Models" by Mark Stamp.
"A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition" by Lawrence Rabiner.



Final exam: Thursday, Dec 17, 10:30 am


Schedule (including projects and midterm) is subject to change.

Moon's dayWoden' s dayFrigga's day

Aug 24

NO CLASS

Aug 26

Background. Introduction
Slides

Read J&M Chapter 1

Aug 28

Preliminaries, history, etc

Aug 31

Introduction to NLTK

Sept 2

Trying out NLTK

In-class activity
Read J&M Section 2.1, no summary necessary

Sept 4

Regular expressions

Project 1, due 9/28

Sept 7

NO CLASS

Sept 9

Words and language models. Probability and statistics background

Sept 11

The noisy channel model

Do the practice problems given in class
Read J&M Sections 4.(1&2)

Sept 14

N-grams
Slides

Read J&M Sections 4.(3&4)

Sept 16

Language models

Sept 18

More about N-grams
Handout

Read J&M Sections 4.(5-7)

Sept 21

Smoothing

Sept 23

Good-Turing smoothing
Slides

Sept 25

Engineering a language model

Sept 28

Linear interpolation

Read J&M 3.(10-12)

Sept 30

Edit distance

Project 1 due

Oct 2

More on edit distance

Oct 5

Information theory. Introduction to information theory. Entropy and perplexity
Slides

Project 2

Oct 7

Review

Oct 9

MIDTERM

Read J&M 4.10-11

Oct 12

The entropy of English
Slides

Read J&M 3.1 and 5.(1-3)

Oct 14

Hidden Markov Models. Lexical categories
Slides

Oct 16

Introduction to Hidden Markov Models

Read J&M 5.(4 & 5)

Oct 19

NO CLASS

Oct 21

More HMMs

Read J&M 6.(1-5)

Oct 23

Part-of-speech tagging

Project 3

Oct 26

Viterbi algorithm

Oct 28

HMM training

Oct 30

More HMM training

Project 4
Read J&M 6.(6-9)

Nov 2

Maximum entropy models

Nov 4

Work on project(s)

Read J&M ch 19 (focus on 19.(1-3))

Nov 6

Lexical semantics. Intrduction to lexical semantics

Nov 9

Applied lexical semantics

In-class activity
Read J&M Ch 12 and 13:1-4 (by Nov 20)

Nov 11

Grammars and parsing. Grammars

Nov 13

More grammars

Nov 16

Guest lecturer: Jonathan Dailey from SIL

Nov 18

Syntactic parsing

Nov 20

Syntactic parsing

Project 5

Nov 23

CKY parsing algorithm

Nov 25

NO CLASS

Nov 27

NO CLASS

Nov 30

Work on project(s)

Dec 2

Applications. Authorship attribution

Dec 4

Work on project(s)

Dec 7

Guest lecturer: Leanne Miller, presenting on Support Vector Machines

Dec 9

More on authorship attribution

Dec 11

Review