CMPSCI 585 Home
Course Description
Textbook & Resources
Syllabus & Slides
Homework assignments
Policies & Grading
|
Introduction to Natural Language Processing
CMPSCI 585
Spring 2004
Syllabus
Exact ordering of topics is subject to change.
MS = Manning & Schutze "Foundations of Statistical Natural Language Processing"
JM = Jurafsky & Martin "Speech and Language Processing"
DATE |
TOPICS |
RELEVANT
READING |
HOMEWORK |
#1, Jan 29, Thu |
Introduction and Overview |
MS Ch 1 |
|
#2, Feb 3, Tue |
Review of probability concepts |
MS Ch 2.1 |
|
#3, Feb 5, Thu |
Classification & Introduction to Information Theory |
MS Ch 2.2 |
HW#1: Naive Bayes document classification |
#4, Feb 10, Tue |
Noisy channel, N-grams, and Smoothing |
MS Ch 6 |
|
#5, Feb 12, Thu |
(continuation of smoothing, and) Collocations |
MS Ch 5 |
|
#6, Feb 17, Tue |
Word sense disambiguation and EM |
MS Ch 7 |
HW#1 due.
HW#2: EM word sense disambiguation |
#7, Feb 19, Thu |
HW Q&A |
Assigned reading of MS Ch 3 |
|
#8, Feb 24, Tue |
Finite state machines
[Guest lecture: Sutton] |
JM Ch 3 |
|
#9, Feb 26, Thu |
Part-of-speech tagging & Hidden Markov models |
MS Ch 10, 9 |
HW#2 due. |
#10, Mar 2, Tue |
HMMs and Baum-Welch |
MS Ch 9 |
HW#3: HMM Viterbi for POS tagging |
#11, Mar 4, Thu |
Detailed example of HMM, with class participation. |
|
|
#12, Mar 9, Tue |
Lexical acquisition (make-up from Feb 19), mid-term review |
MS Ch 8 |
|
#13, Mar 11, Thu |
MIDTERM EXAM |
|
|
Mar 16, Tue |
NO CLASS - Spring Break |
|
|
Mar 18, Thu |
NO CLASS - Spring Break |
|
|
#14, Mar 23, Tue |
Parsing, Chomsky hierarchy, Context-free grammars, top-down and bottom-up parsing |
JM Ch 9
MS Ch 11 .1 |
Project: 1 paragraph proposal due. |
#15, Mar 25, Thu |
The Earley Parser, examples with class participation |
JM Ch 10.4 |
|
#16, Mar 30, Tue |
Probabilistic Context-free Grammars, definition and properties, inside-outside algorithm |
MS Ch 11.2-5 |
HW#3 due.
|
#17, Apr 1, Thu |
Project questions. |
|
Project: 1 page proposal due. |
#18, Apr 6, Tue |
PROJECT PROPOSALS
(and Center for Teaching visitor) |
|
|
#19, Apr 8, Thu |
Parsing with Probabilistic Context-free Grammars, extensions and practical issues |
MS Ch 12 |
|
#20, Apr 13, Tue |
Maximum entropy |
MS Ch 16.2 |
|
#21, Apr 15, Thu |
Information extraction 1 |
|
|
#22, Apr 20, Tue |
Information extraction 2 |
|
|
#23, Apr 22, Thu |
UMASS HOLIDAY
(Optional class: Rm 142)
|
MS Ch 13 |
Project: 1 paragraph progress report due by email. |
#24, Apr 27, Tue |
Machine translation 1
(Slides courtesy of Michael Collins) |
|
|
#25, Apr 29, Thu |
Machine translation 2 , plus Decoding section.
(Slides courtesy of Michael Collins) |
|
|
#26, May 4, Tue |
Model-theoretic approaches to syntax, semantics and logic
[Guest lecture: Chris Potts, Linguistics]
|
|
|
#27, May 6, Thu |
Automatically adding captions to images
[Guest lecture: Victor Lavrenko, CS] |
|
|
#28, May 11, Tue |
TBD
[Guest lecture: TBD] |
|
Project: all reports due. (About four pages on (a) problem, (b) why interesting, (c) approach, (d) evaluation.) |
#29 May 13, Thu |
Project presentations
|
|
|
May 17, 11am |
Optional Exam review |
|
|
May 18, 10:30pm, LGRT 321 |
FINAL EXAM |
|
|
Some slide content from Chris Manning, Jason Eisner, Jan Hajic, Mary Harper, Michael Collins, William Cohen.
|