[yapc] Perl NLP: Stemming and Lemmatizing
YAPC::NA Director
admin at yapcna.org
Wed Apr 18 01:00:02 PDT 2012
Tom Christiansen will give a talk at YAPC::NA_2012 described as:
Perl is used in the NLP (natural language community) for a variety of
tasks. In biomedical texts, words derived from Latin and Greek pose a
big problem for English-language stemmers, because existing standard
algorithms like Porter and Snowball fail to produce the base lemmas
when faced with irregular plurals.Â
This talk reviews the problems with existing tools and presents the
new Lingua::EN::Biolemmatizer module, which interfaces with the
University of Colorados BioLemmatizer code to produce much more
accurate results than were previously available.
[From the YAPC::NA_Blog.]
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.pm.org/mailman/private/yapc/attachments/20120418/7d94b918/attachment.html>
More information about the yapc
mailing list