Semantic map generation from natural-language-text documents

A tangible, non-transitory, machine-readable medium storing instructions that when executed by one or more processors effectuate operations comprising:

• obtaining, with a computer system, a natural-language-text document comprising a first clause and a second clause;
• determining, with the computer system, a first embedding sequence based on n-grams of the first clause and a second embedding sequence based on n-grams of the second clause;
• generating, with the computer system, a first data model object and a second data model object based on the first embedding sequence and the second embedding sequence, wherein:
• the first data model object comprises a first field populated with a first n-gram of the first clause and a second field populated with a first category;
• and
• the second data model object comprises third field populated with a second n- gram of the second clause and a fourth field populated with a second category;
• determining, with the computer system, an association between the first data model object and the second data model object based on a shared parameter of the first and second clauses;
• receiving, with the computer system, a query comprising the first category and the first n-gram;
• causing, with the computer system, a presentation of a visualization of the first and second data model objects in response to receiving the query, the visualization comprising:
• a first shape comprising the first n-gram and the first category;
• a second shape comprising the second n-gram and the second category;
• and
• a third shape comprising a first end that is connected to the first shape and a second end that is connected to the second shape based on the association between the first data model object and the second data model object;
• and
• storing, with the computer system, the first data model object and the second data model object in memory.