Rule development for natural language processing of text

A computing device comprising:

• a processor;
• and
• a non-transitory computer-readable medium operably coupled to the processor, the computer-readable medium having computer-readable instructions stored thereon that, when executed by the processor, cause the computing device to
• select annotated text from a first document of a plurality of annotated documents;
• select an entity rule type from a plurality of entity rule types;
• identify an argument of the selected entity rule type;
• randomly select a value for the identified argument based on the selected annotated text to generate a rule instance;
• apply the generated rule instance to remaining documents of the plurality of annotated documents;
• compute a rule performance measure based on application of the generated rule instance;
• and
• store the generated rule instance and the computed rule performance measure.

A method of defining a rule for natural language processing of text, the method comprising:

• selecting, by a computing device, annotated text from a first document of a plurality of annotated documents;
• selecting, by the computing device, an entity rule type from a plurality of entity rule types;
• identifying, by the computing device, an argument of the selected entity rule type;
• randomly selecting, by the computing device, a value for the identified argument based on the selected annotated text to generate a rule instance;
• applying, by the computing device, the generated rule instance to remaining documents of the plurality of annotated documents;
• computing, by the computing device, a rule performance measure based on application of the generated rule instance;
• and
• storing, by the computing device, the generated rule instance and the computed rule performance measure.