×

Method and apparatus for configurable microplanning

  • US 10,565,308 B2
  • Filed: 08/10/2015
  • Issued: 02/18/2020
  • Est. Priority Date: 08/30/2012
  • Status: Active Grant
First Claim
Patent Images

1. A computer-implemented method for transforming an input data stream comprising raw input data that is expressed in a non-linguistic format into a format that can be expressed linguistically in a textual output, the method comprising:

  • receiving, using a processor, one or more rules written by a user via a user interface, wherein the user interface enables the user to define the one or more rules in at least a first format that is configured to hide linguistic complexities from the user;

    converting, using the processor, the one or more rules in a first format into a set of lexicalization rules in a second format that is configured to be processed by a natural language generation system, wherein the set of lexicalization rules are specified using a microplanning rule specification language that comprises a set of message-level rules and a set of slot-level rules, wherein the microplanning rule specification language is configured to fill syntactic constituents using one or more message-level rules, and wherein message-level rules specify how an overall form of a phrase is to be constructed from message contents and slot-level rules specify how specific entities present in a message should be described or otherwise referred to;

    generating, using the processor, at least one data structure based on the input data stream comprising raw input data that is expressed in a non-linguistic format, wherein the at least one data structure represents a phrase or a simple sentence and is created in an instance in which the input data stream comprises data that satisfies one or more predetermined requirements, wherein the one or more predetermined requirements are selected based in part on a domain associated with the textual output;

    applying, using the natural language generation system operating on the processor, the set of lexicalization rules to the at least one data structure to generate a text specification, wherein the at least one data structure is generated based on the input data stream;

    realizing, using the processor, the text specification to generate the textual output that linguistically describes at least a portion of the input data stream; and

    outputting, using the processor, the textual output to the user interface.

View all claims
  • 4 Assignments
Timeline View
Assignment View
    ×
    ×