Enhancing natural language processing accuracy in computer systems

A computer system for improving abstract summarization with question and answer rewards in a computer system, the computer system comprising:

• one or more computer processors;
• one or more computer readable storage devices;
• program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising:
• program instructions to generate, by a question and answer generator, questions and answers corresponding to a generated summary;
• program instructions to evaluate received answers for the generated questions by analyzing received answers associated with the generated summary against answers received for an original summary;
• program instructions to calculate a reward based on a similarity between answers associated with the generated summary and the original summary;
• and
• program instructions to update a generation model by applying the calculated reward to further train the generation model.

A computer program product for improving abstract summarization with question and answer rewards in a computer system, the computer program product comprising:

• one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising:
• program instructions to generate, by a question and answer generator, questions and answers corresponding to a generated summary;
• program instructions to evaluate received answers for the generated questions by analyzing received answers associated with the generated summary against answers received for an original summary;
• program instructions to calculate a reward based on a similarity between answers associated with the generated summary and the original summary;
• and
• program instructions to update a generation model by applying the calculated reward to further train the generation model, wherein the generation model is a sequence-to-sequence summary generation model.