Automatic neutral point of view content generation

A computer program product for content generation, the computer program product comprising:

• one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
• program instructions to construct, from a set of natural language text documents, a concept tree, a node of the concept tree representing a subject of a subset of the set of natural language text documents (subset), a level of the concept tree corresponding to a degree level of specificity of a subject of a node in the level;
• program instructions to score, for a node in the concept tree (node) using a trained polarity scoring model, a polarity of the subset represented by the node;
• program instructions to add a second set of natural language text documents to the subset, the adding resulting in a modified subset of natural language text documents, the modified subset having a polarity score within a predefined neutral polarity score range;
• program instructions to select, from the modified subset according to a sentence selection parameter, a bin of sentences, a sentence in the bin of sentences extracted from a selected document in the modified subset;
• program instructions to remove, from the bin of sentences, the removing resulting in a filtered bin of sentences, a sentence having a factuality score below a threshold factuality score;
• and
• program instructions to generate, from the filtered bin of sentences using a transformer deep learning narration generation model, a new natural language text document corresponding to the filtered bin of sentences.

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 construct, from a set of natural language text documents, a concept tree, a node of the concept tree representing a subject of a subset of the set of natural language text documents (subset), a level of the concept tree corresponding to a degree level of specificity of a subject of a node in the level;
• program instructions to score, for a node in the concept tree (node) using a trained polarity scoring model, a polarity of the subset represented by the node;
• program instructions to add a second set of natural language text documents to the subset, the adding resulting in a modified subset of natural language text documents, the modified subset having a polarity score within a predefined neutral polarity score range;
• program instructions to select, from the modified subset according to a sentence selection parameter, a bin of sentences, a sentence in the bin of sentences extracted from a selected document in the modified subset;
• program instructions to remove, from the bin of sentences, the removing resulting in a filtered bin of sentences, a sentence having a factuality score below a threshold factuality score;
• and
• program instructions to generate, from the filtered bin of sentences using a transformer deep learning narration generation model, a new natural language text document corresponding to the filtered bin of sentences.

A data processing environment 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 construct, from a set of natural language text documents, a concept tree, a node of the concept tree representing a subject of a subset of the set of natural language text documents (subset), a level of the concept tree corresponding to a level of specificity of a subject of a node in the level;
• program instructions to score, for a node in the concept tree (node) using a trained polarity scoring model, a polarity of the subset represented by the node;
• program instructions to add a second set of natural language text documents to the subset, the adding resulting in a modified subset of natural language text documents, the modified subset having a polarity score within a predefined neutral polarity score range;
• program instructions to select, from the modified subset according to a sentence selection parameter, a bin of sentences, a sentence in the bin of sentences extracted from a selected document in the modified subset;
• program instructions to remove, from the bin of sentences, the removing resulting in a filtered bin of sentences, a sentence having a factuality score below a threshold factuality score;
• and
• program instructions to generate, from the filtered bin of sentences using a transformer deep learning narration generation model, a new natural language text document corresponding to the filtered bin of sentences.

A natural language processing 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 construct, from a set of natural language text documents, a concept tree, a node of the concept tree representing a subject of a subset of the set of natural language text documents (subset), a level of the concept tree corresponding to a level of specificity of a subject of a node in the level;
• program instructions to score, for a node in the concept tree (node) using a trained polarity scoring model, a polarity of the subset represented by the node;
• program instructions to add a second set of natural language text documents to the subset, the adding resulting in a modified subset of natural language text documents, the modified subset having a polarity score within a predefined neutral polarity score range;
• program instructions to select, from the modified subset according to a sentence selection parameter, a bin of sentences, a sentence in the bin of sentences extracted from a selected document in the modified subset;
• program instructions to remove, from the bin of sentences, the removing resulting in a filtered bin of sentences, a sentence having a factuality score below a threshold factuality score;
• and
• program instructions to generate, from the filtered bin of sentences using a transformer deep learning narration generation model, a new natural language text document corresponding to the filtered bin of sentences.