Fast NLP tools Extends ShallowNLP with a dependency parser based on maltparser or the Stanford NN dependency parser This means that constituent trees and coreference, which depends on that, are not available The default setting is to use the Stanford parser with "basic" dependencies Malt produces ONLY Stanford "basic" dependencies, rather than "collapsed" ones User: mihais Date: 1/4/14
Evaluates a model produced by TrainMalt User: mihais Date: 1/5/14
Trains maltparser with basic Stanford dependencies, using LR from liblinear User: mihais Date: 1/4/14