Balie is the open source NLP engine powering YooName. The latest release, called “Ungava” is entirely compatible with YooName. It means that by installing Balie:
- you get a fully functional subset of YooName;
- you are ready to upgrade to YooName (all you need is the extended lexicon and the disambiguation rules).
Ungava release includes named entity recognition model for persons, locations and organizations. Balie scores an average of 78% of f-measure on the standard MUC-7 dataset (see state-of-the-art results).
August 1, 2007 at 2:54 pm |
I haven’t been able to update from CVS yet cause it won’t let me log in for some reason, but the UIMA Annoator is broken when using this release. It it trying to use a method that doesn’t exist any more:
java.lang.NoSuchMethodError: ca.uottawa.balie.Tokenizer.(Ljava/lang/String;Z[Lca/uottawa/balie/NamedEntityTypeEnumI;)V
Hopefully this is fixed in CVS?
August 1, 2007 at 3:05 pm |
You should be able to connect to the CVS anonymously:
cvs -d:pserver:anonymous@balie.cvs.sourceforge.net:/cvsroot/balie login
I just tried it and it worked well (CVS nomenclature recently changed at sourceforge, check the host name)
The UIMA annotator now includes balie.jar in /lib folder, as per PEAR spec. The annotator has therefore no more external dependencies and should not break in the future because of Balie releases.