Page History

Configuration

• Parameter
  summary Model to use for recognition, by default it always uses the latest, but can be configure to use one in specific default --LATEST-- name Model required true

• Parameter
  summary Probability threshold. Will only tag names that match better or equal to the value specified. default .7 name Minimum Probability type double required true

• Parameter
  summary Indicates which tags must be first recognized in order to do the recognition and training name Normalize Tags type string array

  
  
  • This helps to reduce the noise in the text, for example reducing every set of numbers to {number}

Training a Model

Click on the  button to open the "Start Training Run" dialog

• Parameter
  summary Select the Dataset to use as training data name Datasets type boolean required true

• Parameter
  default 200 name Iterations type integer required true

• Parameter
  default 5 name Cut Off type integer required true

• Parameter
  default 2 name Threads type integer required true

• Parameter
  summary Indicates the percentage of failed files during the training of the model default 10 name Error Threshold type integer required true

• Parameter
  default MAXENT_QN name Algorithm

  • Available algorithms

    • MAXENT_QN

    • MAXENT

    • NAIVEBAYES

    • PERCEPTRON

• Parameter
  default 0.00001 name LLThreshold type double required true

• Parameter
  default false name Smoothing type boolean

• Parameter
  default 0.00001 name Smoothing Observation type double

• Parameter
  default false name Gaussian Smoothing type boolean

• Parameter
  default 2 name Gaussian Smoothing Sigma type integer

General Settings