×

Reclassification of training data to improve classifier accuracy

  • US 9,342,588 B2
  • Filed: 06/18/2007
  • Issued: 05/17/2016
  • Est. Priority Date: 06/18/2007
  • Status: Active Grant
First Claim
Patent Images

1. A method of creating a statistical classification model for use with a natural language understanding system, the method comprising:

  • via a processor, processing training data using an existing statistical classification model;

    via the processor, selecting sentences of the training data correctly classified into a selected class of the existing statistical classification model;

    via the processor, assigning each selected sentence of the training data to a fringe group or a core group according to confidence score;

    via the processor, updating the training data by associating the fringe group with a fringe subclass of the selected class and the core group with a core subclass of the selected class;

    via the processor, building a new statistical classification model from the updated training data; and

    via the processor, outputting the new statistical classification model.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×