System and method of automatic template generation

A computer system, comprising:

• a memory;
• a processor, coupled to the memory, the processor configured to:
• receive, by a computer device via a template-generating graphical user interface, a first text fragment, comprising a first identifier of a first text token, wherein the first token comprises one or more words in a natural language and wherein the first token references a first information object from a first category of information objects;
• deriving, by the computer device, a plurality of linguistic characteristics of the first text token, wherein the plurality of linguistic characteristics comprises at least one of grammatical, syntactic, or semantic characteristics of the first text token;
• display, using the template-generating graphical user interface, the plurality of linguistic characteristics of the first token;
• receive, via the template-generating graphical user interface, a first input identifying template attributes from the plurality of the linguistic characteristics of the first information object;
• generate a first template based at least in part on the identified template attributes;
• create a first production rule for the first template;
• apply the first production rule to portions of a first natural language text matching the first template, wherein applying the first production rule comprises:
• identifying portions of the first natural language text that match the first template;
• and
• responsive to identifying the portions of the first natural language text matching the first template, associating the identified portions of the first natural language text with a category of information objects;
• and
• display, using the template-generating graphical user interface, a second information object identified in the first natural language text using the first production rule.

A computer-readable non-transitory storage medium comprising executable instructions that, when executed by a computer system, cause the computer system to:

• receive, by a computer device via a template-generating graphical user interface, a first text fragment, comprising a first identifier of a first text token, wherein the first token comprises one or more words in a natural language and wherein the first token references a first information object from a first category of information objects;
• deriving, by the computer device, a plurality of linguistic characteristics of the first text token, wherein the plurality of linguistic characteristics comprises at least one of grammatical, syntactic, or semantic characteristics of the first text token;
• display, using a template-generating graphical user interface, a plurality of linguistic characteristics of the first token;
• receive, via the template-generating graphical user interface, a first input identifying template attributes from the plurality of the linguistic characteristics of the first information object;
• generate a first template based at least in part on the identified template attributes;
• create a first production rule for the first template;
• apply the first production rule to portions of a first natural language text matching the first template, wherein applying the first production rule comprises:
• identifying portions of the first natural language text that match the first template;
• and
• responsive to identifying the portions of the first natural language text matching the first template, associating the identified portions of the first natural language text with a category of information objects;
• and
• display, using the template-generating graphical user interface, a second information object identified in the first natural language text using the first production rule.