Module train

Train a new model for event or relation detection.

Parameters:

• output - A directory where output files will appear.
• task - If defined, overridable default settings are used for many of the training parameters. Must be one of the supported TEES tasks.
• detector - a Detector object, or a string defining one to be imported
• inputFiles - A dictionary of file names, with keys "train", "devel" and, "test"
• models - A dictionary of file names defining the place for the new models, with keys "devel" and, "test"
• parse - The parse element name in the training interaction XML
• processUnmerging - Use the unmerging step of EventDetector. True, False or None for task default.
• processModifiers - Use the modifier detection step of EventDetector. True, False or None for task default.
• isSingleStage - False for EventDetector, True for a single stage detector.
• bioNLPSTParams - Parameters controlling BioNLP ST format output.
• preprocessorParams - Parameters controlling the preprocessor. Not used for training, but saved to the model for use when classifying.
• exampleStyles - A parameter set for controlling example builders.
• classifierParams - A parameter set for controlling classifiers.
• doFullGrid - Whether all parameters, as opposed to just recall adjustment, are tested in the EventDetector grid search.
• deleteOutput - Remove an existing output directory
• copyFrom - Copy an existing output directory for use as a template
• log - An optional alternative name for the log file. None is for no logging.
• step - A step=substep pair, where the steps are "TRAIN", "DEVEL", "EMPTY" and "TEST"
• omitSteps - step=substep parameters, where multiple substeps can be defined.
• debug - In debug mode, more output is shown, and some temporary intermediate files are saved
• connection - A parameter set defining a local or remote connection for training the classifier