Techniques for automatic generation of natural language text

At least one non-transitory computer-readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method for use in connection with generating text, the method comprising:

• obtaining a plurality of items of content and associated metadata, the associated metadata comprising information indicative of how persuasive at least one of the plurality of items of content is likely to be to a person;
• obtaining a schema specifying a first set of one or more rhetorical relations;
• identifying a second set of one or more rhetorical relations among items of content in the plurality of items of content based, at least in part, on the associated metadata, wherein the second set of rhetorical relations is not in the schema;
• generating a document plan comprising a plurality of rhetorical relations among the items of content in the plurality of items of content, the plurality of rhetorical relations including the first set of rhetorical relations and the second set of rhetorical relations;
• generating an electronic document comprising natural language text based, at least in part, on the document plan;
• and
• providing the electronic document to the person.

A system, comprising:

• at least one computer hardware processor;
• and
• at least one non-transitory computer-readable storage medium storing processor executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform a method for use in connection with generating text, the method comprising:
• obtaining a plurality of items of content and associated metadata, the associated metadata comprising information indicative of how persuasive at least one of the plurality of items of content is likely to be to a person;
• obtaining a schema specifying a first set of one or more rhetorical relations;
• identifying a second set of one or more rhetorical relations among items of content in the plurality of items of content based, at least in part, on the associated metadata, wherein the second set of rhetorical relations is not in the schema;
• generating a document plan comprising a plurality of rhetorical relations among the items of content in the plurality of items of content, the plurality of rhetorical relations including the first set of rhetorical relations and the second set of rhetorical relations;
• generating an electronic document comprising natural language text based, at least in part, on the document plan;
• and
• providing the electronic document to the person.