Ling-367 Computational Tools for Linguists
Semeter: Fall 2006
Time: Tuesday 4:15-6:15PM
Room: CBN 301
Taught by:
George Wilson
email: wilsong@georgetown.edu
office: ICC477
office hours: Tue 3-4, or by appointment
Markus Dickinson
email: mad87@georgetown.edu
office: ICC452
office hours: Mon 12-1, Thu 11-12, or by appointment
Assigments
Syllabus
Schedule
5 Sept - First Class
TBA - Midterm
Resources
BlackBoard
- Course Documents including Lecture Notes
Tools
that will be used in class.
Data
that will be used in class.
Usage Demo from GVW.
NOTE: If you use the demo from off-campus, you will not have
access to all datasets unless you have a username and password.
WordNet
LingPipe
Perl
Perl Programming - example programs
Activeware - You can download perl for Windows or Mac from this site.
Perl - Reference Guide
Introduction to Perl from Perl Training Australia
Perl RegEx Tutorial from University of Georgia
Perl Language Home Page
CPAN Comprehensive Perl Archive Network
Perl Resources and Reviews
Perl Quick reference Guide
Perl monks - tutorials and other useful information
cgi-lib - perl tools for cgi programming
Corpora
Guidelines
for formatting your corpus data
Legal aspects of compiling corpora - Thread on the Linguist List
Note particularly this message containing a Statement on Use
LDC - The Linguistic Data Consortium - Georgetown is now a member.
Project Gutenberg - many free electronic texts, mostly older texts, but very useful
TRAINS - free corpus of speech transcriptions
MiCASE Michigan Corpus of Academic Spoken English
Ulrich Germann's Aligned Parallel French-English Corpus
EuroParl Corpus - 8 language parallel corpus
WHO Media Center - press releases in English and French
BNC British National Corpus
ANC American National Corpus
Leipzig Corpus
/usr/dict/words has a good list of words (lemmas)
Other
Merriam-Webster Dictionary
Dictionary.com Meta-dictionary
OneLook Meta-dictionary
Unicode Code Charts
Unicode Character Names
Easily Confused Words - at InfoPlease.com
Name Description - This is a template for adding more entries