SwiRL-OSX is a Mac OSX compatible version of the original SwiRL system developed by Mihai Surdeanu.
The source is verified to build in OSX Snow Leopard, using gcc 4.2.1.
Make sure you have WordNet installed and the environment variable $WNHOME is set to the root of the installation directory. You can download and install WordNet here, then set $WNHOME accordingly. See example.
$ # If you installed wordnet to /usr/local/WordNet-3.0/ $ export WNHOME='/usr/local/WordNet-3.0/' $ echo $WNHOME /usr/local/WordNet-3.0/
For other build errors, please refer to this FAQ.
SwiRL is a Semantic Role Labeling (SRL) system constructed on top of the full syntactic analysis of text. The syntactic analysis is performed using Eugene Charniak's parser (included in this package). SwiRL trains one classifier for each argument label using a rich set of syntactic and semantic features. The classifiers are learned using one-vs-all AdaBoost classifiers, using Xavier Carreras' AdaBoost software (included in this package).
When tested on the CoNLL evaluation data, SwiRL obtains an F1 measure of 77.44 on the WSJ testing section and of 66.65 on the Brown testing section. The execution time is slightly less than 3 seconds/sentence (includes full parsing and SRL).
Mihai Surdeanu, but this package includes also Eugene Charniak's parser and Xavier Carreras' AdaBoost software.
For installation details, please refer to the original README.