Linguistics 696f
Statistical Natural Language Processing
Handouts:
The handouts above are in PDF format. These can be viewed with Acrobat
Reader, available for free from Adobe.
Web Pages:
Things to Read:
*Some of the items above are available only as postscript. These can be
printed on the u-cluster with a2ps or viewed/printed with
Ghostview (free for all
platforms)
Corpora:
Software:
*The software above has to be compiled and run in a unix/linux
environment. It has all been installed on the u-cluster (where your
university email accounts live), but you can install it on your own
machine as well if you are running some version of Unix, Mac OS-X, or Cygwin. The latter should not
be attempted by the faint of heart!
Other course materials:
- My book manuscript
- programs from book (Note that these are not production quality and
require that you have Perl installed on your system.)
*Some of the programs above have been saved with a .txt
extension. This should be stripped off before running the program. For
example, uniapprox.txt should be renamed
uniapprox.pl. The programs can
be run in several ways; the easiest is perl program-name
(arguments).
Mike Hammond
Dept. of
Linguistics