Please download the dossier by clicking on the dossier button x
×

CONCEPT NOISE REDUCTION IN DEEP QUESTION ANSWERING SYSTEMS

  • US 20140127647A1
  • Filed: 12/05/2012
  • Published: 05/08/2014
  • Est. Priority Date: 11/08/2012
  • Status: Active Grant
First Claim
Patent Images

1. A method for a deep question answering system, the method comprising:

  • computing a concept score for a first concept in a first case received by the deep question answering system, wherein the concept score is based on a machine learning concept model for the first concept;

    excluding the first concept from consideration when analyzing a candidate answer and an item of supporting evidence to generate a response to the first case when the concept score does not exceed a predefined concept minimum weight threshold; and

    increasing, by operation of one or more computer processors, a weight applied to the first concept when analyzing the candidate answer and the item of supporting evidence to generate the response to the first case when the concept score exceeds a predefined maximum weight threshold.

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