From: Steven Bird <sb@cs...> - 2008-06-13 23:10:48
NLTK-Lite 0.9.3 has been released
This version contains an improved WordNet similarity module using
pre-built information content files (included in the corpus
distribution), new/improved interfaces to Weka, MEGAM and
Prover9/Mace4 toolkits, improved Unicode support for corpus readers, a
BNC corpus reader, and a rewrite of the Punkt sentence segmenter
contributed by Joel Nothman. NLTK-Contrib includes an implementation
of incremental algorithm for generating referring expression
contributed by Margaret Mitchell.
NLTK and Google Summer of Code
Jason Narad and Petro Verkhogliad have received sponsorship from
Google Summer of Code to develop NLTK modules for dependency parsing
and for natural language generation. For more information about these
and other ongoing student projects, please see:
The NLTK book will be completed later this year; please send feedback
in whatever way is most convenient (emailed comments, marked-up
hardcopy, reports to the bugtracker at
http://sourceforge.net/tracker/?atid=400896&group_id=30982 ) -- please
help us maximize the usefulness of this book to you.
A new paper about NLTK will appear in an ACL workshop next week:
"Multidisciplinary instruction with the Natural Language Toolkit."
Steven Bird, Ewan Klein, Edward Loper, and Jason Baldridge,
Proceedings of the Third Workshop on Issues in Teaching Computational
Linguistics, Columbus, Ohio, USA.