CSCI 384. Computational Linguistics

Fall 2025
Thomas VanDrunen



Meeting time: MWF 12:55am-2:05pm.
Meeting place: Meyer 129

Office hours: Schedule through Calendly
Contact: 163 Mey Sci; 752-5692; Thomas.VanDrunen@wheaton.edu
http://cs.wheaton.edu/~tvandrun/cs384


Syllabus

Course textbook: Jurafsky and Martin, Speech and Language Processing, 3e

Programming assignment guide

My Calendly page (for office hours)



Final exam: Tues, Dec 16, 10:30-12:30pm


Moon's dayWoden' s dayFrigga's day

Aug 25

NO CLASS

Aug 27

Introduction
Slides

Aug 29

LAB: Python warm-up and NLTK

Sept 1

NO CLASS

Sept 3

Regular expressions

Sept 5

LAB: Chatbot

Sept 8

Edit distance

Sept 10

Information theory

Sept 12

LAB: Autoregressive text generation

Sept 15

Ngrams, language statistics

Sept 17

Language models, smoothing

Sept 19

Linear interpolation

Sept 22

Finish linear interpolation; begin parts of speech

Sept 24

Introduction to hidden Markov models

Sept 26

HMMs

Sept 29

More on HMMs

Oct 1

LAB: HMMs on character-level states

Oct 3

Parsing

Oct 6

LAB: Recursive descent

Oct 8

CKY parsing

Oct 10

LAB: Spelling correction

Oct 13

Review

Oct 15

MIDTERM

Oct 17

ML bootcamp

Oct 20

NO CLASS

Oct 22

NO CLASS

Oct 24

Bag-of-words model; text classification

Oct 27

Naive Bayes classification

Oct 29

LAB: NBC and sentiment analysis

Oct 31

Finish NBC

Nov 3

Stylometry and authorship attribution

Nov 5

LAB: Stylometry

Nov 7

Applied stylometry

Nov 10

Neural nets

Nov 12

LAB: Neural net language models

Nov 14

Vector semantics and embeddings

Nov 17

Word2Vec

Nov 19

More word2vec

Nov 21

RNNs and LTSMs
Slides

Nov 24

Transformers

Nov 26

NO CLASS

Nov 28

NO CLASS

Dec 1

Machine translation
Slides

Dec 3

LAB: Machine translation

Dec 5

Large language models

Dec 8

Large language models

Dec 10

Large language models

Dec 12

Review