Training machine learning based natural language processing for specialty jargon

A machine learning based natural language processor processing process training system, comprising:

• a processor;
• a memory communicatively coupled to the processor, the memory storing instructions causing the processor to:
• assemble a training corpus of natural language terms comprising a set of labeled specialized language terms associated with a specialized subject area;
• generate, with a machine learning based natural language processing process, a database query corresponding to a question comprising at least one specialized language term within the set of labeled specialized language terms;
• determine a cost function value based on one or more differences between the generated database query and contents in a knowledge graph, the knowledge graph mapping terms associated with the set of labeled specialized language terms to corresponding entities associated with one or more elements in the specialized subject area, the terms comprising at least one term different from one term within the set of labeled specialized language terms;
• refine the machine learning based natural language processing process based on feeding back the cost function value;
• process received one or more queries with the refined machine learning based natural language processing process to create one or more database queries directed to answering one or more questions associated with the received one or more queries;
• and
• present the answer.

A non-transitory computer medium having stored thereon instructions for training a machine learning based natural language processing process to process specialized language terms, the instructions comprising computer readable program code which when executed by one or more processors, cause the one or more processors to:

• assemble a training corpus of natural language terms comprising a set of labeled specialized language terms associated with a specialized subject area;
• generate, with the machine learning based natural language processing process, a database query corresponding to a question comprising at least one specialized language term within the set of labeled specialized language terms;
• determine a cost function value based on one or more differences between the generated database query and contents in a knowledge graph, the knowledge graph mapping terms associated with the set of labeled specialized language terms to corresponding entities associated with one or more elements in the specialized subject area, the terms comprising at least one term different from one term within the set of labeled specialized language terms;
• refine the machine learning based natural language processing process based on feeding back the cost function value;
• process received one or more queries with the refined machine learning based natural language processing process to create one or more database queries directed to answering one or more questions associated with the received one or more queries;
• and
• present the answer.