A plugin for the GATE language technology framework for training and using machine learning models. Currently supports Mallet (MaxEnt, NaiveBayes, CRF and others), LibSVM, Scikit-Learn, Weka, and DNNs through Pytorch and Keras.
The optional outputAS parameter in the application PRs is meant to allow new (copies) of the original instance annotations be created with the target feature set on them, instead of the default behaviour of updating or adding the target feature on the original instance annotation.
This does not seem to work prooperly.
The optional outputAS parameter in the application PRs is meant to allow new (copies) of the original instance annotations be created with the target feature set on them, instead of the default behaviour of updating or adding the target feature on the original instance annotation. This does not seem to work prooperly.