CMPSCI 585 Home

Course Description
Textbook & Resources
Syllabus & Slides
Homework assignments
Policies & Grading

Introduction to Natural Language Processing

CMPSCI 585
Fall 2004

Syllabus

Key:
MS = Manning & Schutze "Foundations of Statistical Natural Language Processing"
JM = Jurafsky & Martin "Speech and Language Processing"
HW = short written homework
PA = programming assignment

Exact ordering of topics is subject to change.

DATE TOPICS RELEVANT
READING
HOMEWORK &
PROGRAMMING
#1, Sep 9, Thu Introduction and Overview
(Handout)
MS Ch 1  
#2, Sep 14, Tue Grammars: Chomsky hierarchy, context free grammars, bottup-up and top-down parsing. MS Ch 3
MS Ch 11 .1
(JM Ch 9)
HW#1 out: Linguistics & CFGs
#3, Sep 16, Thu Deterministic Parsing JM Ch 10.4

PA#1 out:
Simple CYK parser
Sample data

#4, Sep 21, Tue Review of probability concepts
[Guest lecturer: Wei Li]
MS Ch 2.1  
#5, Sep 23, Thu Classification & Intro to Information Theory
[Guest lecturer: Aron Culotta]
MS Ch 2.2 HW#1 in.
HW#2 out: Probabilities
#6, Sep 28, Tue Noisy-channel, N-grams models, smoothing MS Ch 6 PA#1 in.
PA#2 out: Naive Bayes spam filtering. Sample code skeleton.
#7, Sep 30, Thu Collocations & clustering MS Ch 5, 8  
#8, Oct 5, Tue Word sense disambiguation & EM MS Ch 7 HW#2 in.
#9, Oct 7, Thu Lexical acquisition MS Ch 10, 9

#10, Oct 12, Tue

Part-of-speech tagging, HMMs and the Viterbi algorithhm MS Ch 9 PA#2 in.
HW#3 out: Smoothing...EM
PA#3 out: HMM POS tagger
#11, Oct 14, Thu HMMs #2 MS Ch 9  
#12, Oct 19, Tue Named entity recognition and Information Extraction    
#13, Oct 21, Thu Discriminative models: MaxEnt MS Ch 16.2 HW#3 in.
#14, Oct 26, Tue Midterm review
  PA#3 in.
Project: one paragraph proposal due.
#15, Oct 28, Thu MIDTERM EXAM    
#14, Nov 2, Tue Probabilistic Context-free Grammars, definition and properties, inside-outside algorithm MS Ch 11.2-5  
#15, Nov 4, Thu Parsing with Probabilistic Context-free Grammars MS Ch 12 Project: 1 page proposal due.
#16, Nov 9, Tue PROJECT PROPOSALS    
#17, Nov 11, Thu NO CLASS - Veterans' Day    
#18, Nov 16, Tue Forward-Backward and confidence estimation
   
#19, Nov 18, Thu Model-theoretic approaches to syntax, semantics and logic
[Guest lecture: Chris Potts, Linguistics]
  Project: one paragraph progress report due by email.
#20, Nov 23, Tue Tree adjoining grammars
[Guest lecture: Rajesh Bhatt, Linguistics]
   
#21, Nov 25, Thu NO CLASS - Thanksgiving holiday    
#22, Nov 30, Tue Information extraction 2:
coreference, string edit distance, and relations
  HW#4 out.
#23, Dec 2, Thu

Machine Translation

   
#24, Dec 7, Tue Question Answering   HW#4 in.
#25, Dec 9, Thu PROJECT PRESENTATIONS    
#26, Dec 14, Tue

NO CLASS - READING PERIOD BEGINS

  Project write-up in.
?? FINAL EXAM
   

Some slide content from Chris Manning, Jason Eisner, Jan Hajic, Mary Harper, Michael Collins, William Cohen.