Automated novel concept extraction in natural language processing

A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:

• program instructions to extract, from a natural language document using a natural language concept analyzer, a set of natural language input concepts, an input concept in the set of natural language input concepts comprising a natural language idea conveyed in text of the natural language document;
• program instructions to generate, using a query generation model, a query corresponding to the set of natural language input concepts, the query comprising a regular expression representative of text to be searched for within a natural language corpus;
• program instructions to generate, using the query generation model, a second query corresponding to the set of natural language input concepts, the second query including a synonym for a word within the query;
• program instructions to extract, from a set of natural language results using the natural language concept analyzer, a set of natural language output concepts, a result in the set of natural language results comprising a portion of narrative text within the natural language corpus, the result identified by searching the natural language corpus using the query and the second query;
• program instructions to score, using the set of natural language input concepts and the set of natural language output concepts, the input concept as a novelty concept, the scoring resulting in a score, the score denoting a degree to which the input concept is external to a boundary defined by the set of natural language output concepts;
• and
• program instructions to generate, responsive to the score being below a threshold score, a third query corresponding to a modified set of natural language input concepts, the modified set of natural language input concepts modified using the scored novelty concept.

A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

• program instructions to extract, from a natural language document using a natural language concept analyzer, a set of natural language input concepts, an input concept in the set of natural language input concepts comprising a natural language idea conveyed in text of the natural language document;
• program instructions to generate, using a query generation model, a query corresponding to the set of natural language input concepts, the query comprising a regular expression representative of text to be searched for within a natural language corpus;
• program instructions to generate, using the query generation model, a second query corresponding to the set of natural language input concepts, the second query including a synonym for a word within the query;
• program instructions to extract, from a set of natural language results using the natural language concept analyzer, a set of natural language output concepts, a result in the set of natural language results comprising a portion of narrative text within the natural language corpus, the result identified by searching the natural language corpus using the query and the second query;
• program instructions to score, using the set of natural language input concepts and the set of natural language output concepts, the input concept as a novelty concept, the scoring resulting in a score, the score denoting a degree to which the input concept is external to a boundary defined by the set of natural language output concepts;
• and
• program instructions to generate, responsive to the score being below a threshold score, a third query corresponding to a modified set of natural language input concepts, the modified set of natural language input concepts modified using the scored novelty concept.