Package opennlp.tools.ml.maxent

Class GISTrainer

  • All Implemented Interfaces:
    Trainer, EventTrainer
    public class GISTrainer
extends AbstractEventTrainer
    An implementation of Generalized Iterative Scaling (GIS).

    The reference paper for this implementation was Adwait Ratnaparkhi's tech report at the University of Pennsylvania's Institute for Research in Cognitive Science, and is available at ftp://ftp.cis.upenn.edu/pub/ircs/tr/97-08.ps.Z.

    The slack parameter used in the above implementation has been removed by default from the computation and a method for updating with Gaussian smoothing has been added per Investigating GIS and Smoothing for Maximum Entropy Taggers, Clark and Curran (2002). http://acl.ldc.upenn.edu/E/E03/E03-1071.pdf.

    The slack parameter can be used by setting useSlackParameter to true. Gaussian smoothing can be used by setting useGaussianSmoothing to true.

    A Prior can be used to train models which converge to the distribution which minimizes the relative entropy between the distribution specified by the empirical constraints of the training data and the specified prior. By default, the uniform distribution is used as the prior.

    • Constructor Detail

      • GISTrainer

        public GISTrainer()
        Initializes a GISTrainer.

        Note:
        The resulting instance does not print progress messages about training to STDOUT.

    • Method Detail

      • setSmoothing

        public void setSmoothing​(boolean smooth)
        Sets whether this trainer will use smoothing while training the model.

        Note:
        This can improve model accuracy, though training will potentially take longer and use more memory. Model size will also be larger.

        Parameters:
        smooth - true if smoothing is desired, false if not.

      • setSmoothingObservation

        public void setSmoothingObservation​(double timesSeen)
        Sets whether this trainer will use smoothing while training the model.

        Note:
        This can improve model accuracy, though training will potentially take longer and use more memory. Model size will also be larger.

        Parameters:
        timesSeen - The "number" of times we want the trainer to imagine it saw a feature that it actually didn't see

      • setGaussianSigma

        public void setGaussianSigma​(double sigmaValue)
        Sets whether this trainer will use smoothing while training the model.

        Note:
        This can improve model accuracy, though training will potentially take longer and use more memory. Model size will also be larger.

        Parameters:
        sigmaValue - The Gaussian sigma value used for smoothing.

      • trainModel

        public GISModel trainModel​(ObjectStream<Event> eventStream,
                           int iterations,
                           int cutoff)
                    throws IOException
        Trains a GIS model on the event in the specified event stream, using the specified number of iterations and the specified count cutoff.
        Parameters:
        eventStream - A stream of all events.
        iterations - The number of iterations to use for GIS.
        cutoff - The number of times a feature must occur to be included.
        Returns:
        A trained GISModel which can be used immediately or saved to disk using an GISModelWriter.
        Throws:
        IOException

      • trainModel

        public GISModel trainModel​(int iterations,
                           DataIndexer di)
        Trains a model using the GIS algorithm.
        Parameters:
        iterations - The number of GIS iterations to perform.
        di - The DataIndexer used to compress events in memory.
        Returns:
        A trained GISModel which can be used immediately or saved to disk using an GISModelWriter.
        Throws:
        IllegalArgumentException - Thrown if parameters were invalid.

      • trainModel

        public GISModel trainModel​(int iterations,
                           DataIndexer di,
                           int threads)
        Trains a model using the GIS algorithm.
        Parameters:
        iterations - The number of GIS iterations to perform.
        di - The DataIndexer used to compress events in memory.
        threads - The number of thread to train with. Must be greater than 0.
        Returns:
        A trained GISModel which can be used immediately or saved to disk using an GISModelWriter.
        Throws:
        IllegalArgumentException - Thrown if parameters were invalid.

      • trainModel

        public GISModel trainModel​(int iterations,
                           DataIndexer di,
                           Prior modelPrior,
                           int threads)
        Trains a model using the GIS algorithm.
        Parameters:
        iterations - The number of GIS iterations to perform.
        di - The DataIndexer used to compress events in memory.
        modelPrior - The Prior distribution used to train this model.
        Returns:
        A trained GISModel which can be used immediately or saved to disk using an GISModelWriter.
        Throws:
        IllegalArgumentException - Thrown if parameters were invalid.