Ontology driven dictionary generation and ambiguity resolution for natural language processing

  • US 9,922,024 B2
  • Filed: 05/31/2016
  • Issued: 03/20/2018
  • Est. Priority Date: 06/12/2012
  • Status: Active Grant
First Claim
Patent Images

1. A computer implemented method for natural language processing ambiguity resolution, comprising:

  • storing, in computer memory, an ontological library, wherein the ontological library stores an ontological hierarchy of classes and sub-classes, each class or sub-class representing a distinct grammatical function, and wherein the ontological library specifies a set of grammatical rules, wherein the grammatical rules store permissible positional relations between ontological classes and sub-classes;

    generating, using a computer processor, a dictionary for each class and subclass by compiling word instances belonging to the class or sub-class;

    receiving, using the processor, a phrase comprising at least one ambiguous word to be processed that is associated in the dictionary with at least one class and at least two sub-classes;

    annotating, using the processor, the ambiguous word with possible classes and sub-classes to which the ambiguous word belongs based on the generated dictionaries;

    retrieving, from the ontological library using the processor, grammatical rules associated with possible classes and sub-classes to which the ambiguous word belongs;

    eliminating, using the processor, one or more possible classes or sub-classes based on the retrieved grammatical rules and possible classes of one or more words in the phrase proximate to the ambiguous word; and

    determining, using the processor, a class and sub-class for the ambiguous word based on a possible class or sub-class not eliminated.

View all claims

    Thank you for your feedback