we have decided to make the TOSCA/LOB tagger generally available.
This tagger takes as input English text, possibly containing SGML
markup, and produces tagged text, both in a multi-column and in an
SGML/TEI format. The tagset used is basically the LOB tagset (about
130 tags plus ditto-tags), although with a few very slight adjustments.
The system is currently only available for MS-DOS. It can be downloaded
freely from
ftp://lands.let.kun.nl/pub/tosca/tlbtag
Of course, we are interested to learn what you use the tagger for and
what your experiences are.
We hope to produce an even better tagger for this tagset reasonably soon
and will report on this list when it is ready.
Best wishes,
Hans van Halteren