Natural Language Computing
Resources for Assignment 1
Check the 401
home page and the course bulletin board
regularly for course announcements, assignment hints, etc.
The Brown Corpus (gzipped tar file for
/ Linux, 2.9Mb)
The Brown Corpus (zipped file for PC,
The Brill tagger
tar file for Unix / Linux, 1.3Mb)
Brill tagger for Windows - you have a few options here:
C4.5 package, release
145Kb). The link is at the bottom of Professor Quinlan's home page; you
get a gzipped tar file with source code and installation instructions.
Note restrictions on distribution! This package runs under Unix / Linux
only; not for Windows.
Download Python from the Python
website for all platforms. Remember to test your scripts on
before submitting -- your assignment
must work on CDF in order to
get any marks!
Last modified by Gerald Penn, 10 January 2010
This web-page was adapted from the web-page for another course,
created by Graeme Hirst.