The Department of Computer Science & Engineering |
CSE 740:
SEMINAR: CONTEXTUAL VOCABULARY ACQUISITION Fall 2004 |
http://www.cse.buffalo.edu/~rapaport/740/F04/syl.html
)
Last Update: 5 October 2004
Note: or material will be highlighted in future versions. |
We are developing a computational theory of how natural-language-understanding systems can automatically acquire new vocabulary by determining from context the meaning of words that are unknown, misunderstood, or used in a new sense, and adapting the algorithms for doing this to a curriculum so that these methods can be taught to students in a classroom setting.
We are:
(a) extending and developing algorithms for computational contextual vocabulary acquisition (CVA): learning, from context, meanings for unfamiliar words: nouns (including proper nouns), verbs, adjectives, and adverbs,
(b) unifying a disparate literature on the topic of CVA from psychology, first- and second-language (L1 and L2) acquisition, and reading science, in order to help develop these algorithms, and
(c) using the knowledge gained from the computational CVA system to build and to evaluate the effectiveness of an educational curriculum for enhancing readers' abilities to use deliberate (i.e., non-incidental) CVA strategies: teaching methods and guides, materials for teaching and practice, and evaluation instruments.
The knowledge gained from case studies of students using our CVA techniques feeds back into further development of our computational theory.
The seminar will involve reading research literature on CVA from
computational linguistics, psychology, and education; using
the
SNePS
knowledge representation and reasoning system, and/or
using natural-language-processing techniques such
as ATN (augmented-transition-network) grammars.
PREREQUISITE:
Graduate standing, or permission of instructor.
SNePS Tutorial assigned
SNePS
Research Group
SNePS TUTORIAL REPORT DUE!
SNePS TUTORIAL REPORT DUE!
student progress reports
Each critique should consist of:
These papers will be read and recorded, but not graded. However, the
number that you do satisfactorily will be factored into your
final grade.
In the real world, you will be expected to write papers, either for
presentation
at conferences, publication in journals, or presentation to your boss or
co-workers. No one reads computer programs except the programmer him-
or herself,
or someone else who has to modify the program. Users and other people
want to
read about the program, what it does, how it works, etc., and to see
it in action. Consequently, the main product
of your work is the paper, not the program! In the paper, you should
say what you have done, and say (in English summary, not in programming
detail) how you
have done it. It should also include annotated examples of your
program in
action. These should be well chosen to illustrate the range of
performance of
your program. The examples should not be redundant, nor included merely
because they look complicated. Each example should illustrate a
particular
ability of your program. Nevertheless, the reader will assume that your
program does nothing interesting that isn't illustrated!
You should read Goldfain, Albert (2003), "Computationally
Defining 'harbinger' via Contextual
Vocabulary Acquisition" [PDF], to see an example of a such a paper.
Any program listings should either be presented as
figures throughout the paper, or as an appendix. In either case, any
listings should be included as documentation for what you say in the paper.
Thus, each report must consist of the following components:
Any incompletes that I might give, in a lapse of judgment :-),
will have to be made up by the end of the
Spring 2004
semester. This is one semester SOONER than the default university
policy.
For more information on Incomplete policies, see the web page,
"Incompletes".
PROFESSOR:
Dr. William J. Rapaport, 214 Bell Hall, 645-3180 x 112,
rapaport@cse.buffalo.edu
Office Hours:
Tuesdays, 2:00-2:50 p.m.;
Fridays, 1:00-1:50 p.m.;
and by appointment.
CLASS MEETINGS:
CLASS INSTRUCTOR REGIS. NO.
DAYS HOURS LOCATION
Seminar Rapaport 464044
Tuesdays 9:30 a.m. - 12:30 p.m.
Baldy 45
IMPORTANT DATES
& TENTATIVE SCHEDULE:
Note: I have adjusted
some of the dates below to reflect what
we actually did, rather than on what I had hoped to do:-)
DAY
MONTH
DATE
TOPIC
READINGS T
Aug
31
Intro to CVA project;
discuss individual projectsRapaport & Ehrlich 2000
Rapaport & Kibby 2002b
Rapaport (forthcoming)T
Sep
7
The CVA Project.
Intro to the SNePS KRR systemShapiro & Rapaport 1987
Shapiro & Rapaport 1995
Martins 2002M
13
Presentation by Dima Dligach
on "SNePS and WordNet"
for CVA
1-3 p.m.,
Bell 242 T
14
SNePS (cont'd.)
CVA readings
T
21
SNePS (cont'd.)
T
28
SNePS & CVA
T
Oct
5
SNePS & CVA (concluded)
student progress reports begin
T
12
student progress reports
continue till end of semester
F
Oct
22
Last Day to Resign
T
Dec
7
Last Class: summary reports
Th
Dec
16
FINAL REPORTS DUE
ATTENDANCE, NEWSGROUP:
SUMMARIES OF CVA READINGS
"You can lead a horse to water, but you can't make him drink." -- American Proverb
PROJECT & FINAL REPORT
HOW TO READ
For advice on how to read technical papers in any field (including
computer science, psychology, education, etc.), see
"How to Read (a Computer Science Text)".
HOW TO STUDY
For general advice on how to study for any course, see my web page,
"How to Study".
HOW TO WRITE
For general advice on how to prepare written reports, see my web page,
"How to
Write"
GRADING:
Since this is a seminar, it will be graded on an S/U basis. However, my
determination of S vs. U
will be determined by a weighted average of
your attendance, seminar presentations, seminar participation, CVA-paper critiques,
and final report.
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 :-)
ACADEMIC INTEGRITY:
While it is acceptable to discuss general
approaches with your fellow students, the work you turn in must be your
own. It is the policy of this department that any violation of
academic integrity will
result in an F for the course, that all departmental
financial support including teaching
assistanceship, research assistanceship, or scholarships be
terminated, that notification of this
action be placed in the student's confidential
departmental record, and that the student be
permanently ineligible for future departmental financial
support. If you have any
problems doing the assignments, consult
Prof. Rapaport. Please be sure to read the webpage,
"Academic Integrity: Policies and Procedures", which spells out all the
details of this, and related, policies.
Copyright © 2004 by
William J. Rapaport
(rapaport@cse.buffalo.edu)
file: 740/F04/syl-2004-10-05.html