Ontological categorization of question concepts from document summaries

A computer system including one or more processors and one or more computer storage media, the computer system comprising:

• a document analyzer that analyzes documents and identifies entities and relationships among entities in text of the documents, wherein the document analyzer also identifies assertions based on the entities and relationships identified from the text of the documents;
• a question generator that inverts the assertions to generate a plurality of questions that may be answered by the assertions;
• and
• a concept/topic engine that identifies concepts and/or topics associated with the plurality of questions and clusters questions around the concepts and/or topics.

One or more computer-readable media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform a method comprising:

• receiving one or more documents;
• parsing the one or more documents to identify sentences;
• analyzing the sentences to identify a subset of the sentences as important sentences indicative of an event or topic discussed by the one or more documents;
• identifying entities and relationships among the entities from text of the important sentences;
• creating an entity-relationship graph based on the identified entities and relationships, wherein nodes in the entity-relationship graph represent entities and wherein edges between nodes in the entity-relationship graph represent relationships between entities;
• identifying a plurality of assertions by analyzing the entity-relationship graph;
• inverting the plurality of assertions to generate a plurality of questions;
• generating a question graph based on the plurality of questions;
• analyzing the questions in the questions graph to identify relevant concepts and/or topics associated with the questions and clustering the questions around the relevant concepts and/or topics;
• and
• generating a combined graph that allows traversal among the concepts and/or topics, the questions, the assertions, and the one or more documents.