The Department of Computer Science & Engineering
cse@buffalo
CSE/LIN 675: COMPUTATIONAL LINGUISTICS - Spring 2000

SYLLABUS

(Available on the Web at: http://www.cse.buffalo.edu/~rapaport/675w/syl.html)

Last Revised: 17 April 2000

NEW material is highlighted

Other relevant links:

PREREQUISITE:

The official prerequisite is CSE 572 or permission of instructor.

Although knowledge of a programming language will not be required, most students will either be graduate students in Computer Science and Engineering who have had a graduate-level introduction to artificial intelligence (similar to CSE 572), or graduate students in Linguistics, or graduate students in any of the other cognitive sciences (such as Philosophy, Psychology, Communicative Disorders and Sciences, Anthropology, etc.) who feel that their knowledge of either computer science or linguistics is sufficient for them to participate in the course.

PROFESSOR:

Dr. William J. Rapaport, 214 Bell Hall, 645-3180 x 112, rapaport@cse.buffalo.edu

Office Hours: Mondays, 2-3 p.m., and by appointment.

CLASS MEETINGS:

REGISTRATION #DAYSHOURSLOCATION
CSE: 495892
LIN: 012297
MWF10:00 - 10:50 a.m. Capen 260

TEXTS:

  1. Required:

  2. Recommended (available at the University Bookstore):

  3. On Reserve at SEL/UGL:

COURSE DESCRIPTION:

This course will be an introduction to the field of Computational Linguistics. It is an appropriate sequel to CSE 572, Knowledge-Based Artificial Intelligence (formerly, Introduction to Artificial Intelligence), or to an introductory graduate-level linguistics course. Topics to be covered will include some or all of the following: the nature of natural-language "competence" (by which I include both understanding and generation), basic syntactic parsing techniques (including augmented-transition-network grammars and deterministic parsing), semantic interpretation, and natural-language generation.

COURSE REQUIREMENTS

Class meetings will consist of lectures, general discussion, and discussion of assigned questions.

Students should notify the instructor within the first two weeks of class if they have a disability which would make it difficult to carry out course work as outlined (requiring note-takers, readers, extended test time).

There are two main requirements:

  1. You must attend virtually all classes, actively participate in class discussions, and turn in all required assignments on time. All assignments and their due dates will be announced in class. (Therefore, be sure to get a classmate's phone number (for instance, 1 or 2 people sitting next to you in class, whoever they are!), so that you will not miss assignments in the unlikely event that you miss a class :-) Assignments will be collected and recorded, but not graded; they will serve as a focus for class discussions. Therefore, no late assignments will be accepted. There may be some small programming-project assignments; these will be team efforts.

  2. There will be a term project. This will be a 10-15-page, "typed", double-spaced report (which may, but need not, include an appendix detailing a computational implementation).

    The report might be a review of the literature on some topic, a discussion of some topic not covered fully in class (e.g., connectionist approaches to computational linguistics, or one of the omitted chapters from the text, or a discussion of another topic of your choice, or an implementation of one or more appropriate algorithms from the text, or a team project (such as an implementation of a "full" natural-language-understanding system, with each team member being responsible for a module), or a computational implementation of your choice. If several of you choose to work together on a team project, your report must include a statement clearly outlining each person's contribution. The final report for an implementation project must include an appendix (beyond the 10-15-page report itself) with annotated sample runs and the commented program code.

    Your topic must be approved by me in advance, and a proposal (perhaps in the form of an extended summary) of 6-8 "typed", double-spaced pages or--even better--a first draft must be turned in no later than Monday, March 13.

    The term project is due no later than Thursday, May 4 (= the first day of final exams). Late projects will be accepted at a full-letter-grade-per-day discount (e.g., an A project, 1 day late, gets a B, not an A-).

READING AND STUDYING:

  1. I strongly urge you to read as much of the text as possible, including those sections that we do not cover in the course.
  2. Not all assigned readings will be covered in lecture (in lecture, we will only cover interesting or hard material, plus occasionally material that is not in the text), but you are responsible for all assigned material in the text, supplementary readings, and lectures.
  3. See "How to Read (a Computer Science Text)".
  4. For general advice on how to study for any course, see my web page, "How to Study".

GRADING:

Class attendance/participation 25%
Assignments 25%
Project 50%
Total 100%

Incompletes:

It is University policy that a grade of Incomplete is to be given only when a small amount of work or a single exam is missed due to circumstances beyond the student's control, and that student is otherwise doing passing work. I will follow this policy strictly! Thus, you should assume that I will not give incompletes :-) Any incompletes that I might give, in a lapse of judgment :-), will have to be made up by the end of the Fall 2000 semester. For more information on Incomplete policies, see the web page, "Incompletes".

TENTATIVE AND ACTUAL SCHEDULE, IMPORTANT DATES, and READINGS:

DatesTopicsRequired Readings
(J&M)
Optional Readings
Jan 19CCS Speaker:
Richard Aslin

UR Center for Visual Science
"Statistical Learning
in Linguistic and
Non-linguistic
Domains"
2-3:30pm
280 Park
Jan 19-Jan 26introductionCh. 1 Cole, overview chapters;
GJW, Pt. VI
Jan 26-Feb 4regular expressions,
finite-state automata
Ch. 2 Cole, 11.6, 12.4;
Eliza handouts
Jan 26 CCS Speaker:
Len Talmy

Linguistics, UB
"Language Structure
and Consciousness"
2-3:30pm
280 Park
Feb 4-Feb 7morphology,
finite-state transducers
Ch. 3 Cole, 3.2
Feb 9word classes§8.1Cole, as above
Feb 9-Feb 11context-free grammarsCh. 9 Cole, 3.3, 3.6, 3.7, 11.4
Feb 11-Feb 23parsing CFGsCh. 10GJW, Chs. 3, 4, 7
Feb 23 CCS Speaker:
Jennifer Stolz

Psychology, U. Waterloo
"On the Joint Effects
of Attention and
Word Recognition:
The Relations
between Resources
and Meaning"
2-3:30pm
280 Park
Feb 23-Mar 29augmented transition networksGJW, Ch. 5 (!);
other handouts
as above
Fri, Mar 3NO LECTURE
Mar 4-Mar 12SPRING BREAK
Mon, Mar 13LAST DATE TO TURN IN
TERM-PAPER PROPOSAL
Fri, Mar 17LAST "R" DATE
Wed, Mar 22UB CSE Grad Conference
Wed, Mar 22 CCS Speaker:
Paul Luce

UB Psychology
"Probabilistic Phonotactics, Neighborhood Activation, and Spoken Word Recognition: An Adaptive Resonance Perspective"2-3:30pm
280 Park
Mar 29-Apr 5features,
unification
Ch. 11GJW, Ch. 8;
and as above
Apr 5-Apr 10representing meaningCh. 14 Cole, 3.5;
GJW, Pt. II
Apr 12CCS Speaker:
Nick Cercone

Univ. of Waterloo Computer Science
"Natural Language Access to Relevant Information on the Internet" 2-3:30pm
280 Park
Apr 12-Apr 19semantic analysisCh. 15 as above
Apr 19CCS Speaker:
Peter W. Jusczyk

Johns Hopkins Psychology
NEW"Infants' use of Multiple Cues to Segment Words from Fluent Speech" 2-3:30pm
280 Park
Apr 21-Apr 28natural-language processing
in SNePS
handouts
Mon, May 1LAST CLASS;
summary & review
Thu, May 4LAST DATE TO TURN IN
TERM PROJECT

ACADEMIC HONESTY:

While it is acceptable to discuss general approaches with your fellow students, the work you turn in must be your own. If the work of two or more students appears unjustifiably similar, penalties (ranging from an F in the assignment to an F in the course) will be assessed to all concerned. If you have any problems doing the homeworks or projects, consult Prof. Rapaport. Also see the webpage, "Academic Integrity"


William J. Rapaport (rapaport@cse.buffalo.edu)
file: 675w/syl.17ap00.html