Corpora: POS Windows taggers and collocations summary

Michael Nelson (mnelson@ra.abo.fi)
Thu, 8 Apr 1999 20:22:39 +0300 (EET DST)

Once again many thanks to all who replied to my query about POS taggers for
Windows and collocation statistics. Here are the replies I got.

Micahel Barlow wrote that he has a program for collocational stats but it is
not ready yet.
Michael Barlow,
barlow@rice.edu
www.ruf.rice.edu/~barlow

_____________________________________________

Wolfgang Lezius wrote:

If you're working on German texts, my tagger (including morphology tool)
might be interesting. It's freely available:

www-psycho.uni-paderborn.de/lezius/

If you're working on English: The Brill tagger is available on Windows
platforms. There have been some mails on this list about it.

wolfgang@lezius.de

________________________________________________
Gilles Souvay wrote:

You can download Brill's tagger under Windows95/98 (version to come will
also run under WNT) at
http://jupiter.inalf.cnrs.fr/Winbrill/

---
Best regards
Gilles.Souvay@inalf.cnrs.fr

___________________________________________________ Paul Rayson wrote:

We are currently porting CLAWS from UNIX to Windows and I hope it will be available in the next 2 or 3 months.

More info on the UNIX version at

http://www.comp.lancs.ac.uk/ucrel/claws/

___________________________________________________

Oliver mason wrote:

For POS tagging:

QTAG (http://www.clg.bham.ac.uk/oliver/java/qtag/) is written in Java and thus works under Windows as well as on Unix. It is free for non-commercial purposes and not too expensive if you want to use it commercially.

> 2. Is there a program available, again under Windows, that can give me t,z > and MI scores for collocational significance? I have developed a corpus access tool called Qwick, also in Java. At the moment it is only available on the BNC sampler CD ROM (with a pre-indexed sample of 2.5 million words of British English), but I will soon (probably about next week) make it available for downloading from our website (without the data, as I cannot distribute that).

Qwick gives you a choice of seven or eight different scores, including several variants of MI,

-- 
//\\ computer officer | corpus research | department of english | school of  -
//\\ humanities | university of birmingham | edgbaston | birmingham b15 2tt  -
\\// united kingdom | phone +44-(0)121-414-6206 | fax +44-(0)121-414-5668/\  -
\\// mobile 07050 104504 | http://www-clg.bham.ac.uk | o.mason@bham.ac.uk\/  -