Identification and rejection of meaningless input during natural language classification

  • US 7,707,027 B2
  • Filed: 04/13/2006
  • Issued: 04/27/2010
  • Est. Priority Date: 04/13/2006
  • Status: Active Grant
  • ×
    • Pin Icon | RPX Insight
    • Pin
First Claim
Patent Images

1. A method for generating a natural language statistical model comprising:

  • receiving, at at least one system comprising a combination of hardware and software, a set of training data comprising unigrams identified as being individually meaningless;

    assigning, via the at least one system, at least a portion of the unigrams identified as being meaningless to a first n-gram class selected from a plurality of n-gram classes; and

    processing the classified training data via the at least one system to generate the natural language statistical model.

View all claims

    Thank you for your feedback