https://hdl.handle.net/1721.1/119476 Sat, 04 Apr 2026 13:34:01 GMT 2026-04-04T13:34:01Z https://hdl.handle.net/1721.1/121129 Automated Question Generation System for Genesis Lala, Sayeri Automatic Question Generation systems automatically generate questions from input such as text. This study implements an Automated Question Generation system for Genesis, a program that analyzes text. The Automated Question Generation system for Genesis outputs a ranked list of questions over content Genesis does not understand. It does this using a Question Generation Module and Question Ranking module. The Question Generation Module determines what content Genesis does not understand and generates questions using rules. The Question Ranking Module ranks the questions by relevance. This Automated Question Generation system was evaluated on a story read by Genesis. The average question relevance among the top 10 generated questions was 2.41 on a scale of 1-3, with 3 being most relevant. 53.8% of subjects ranked questions in the same order as the Question Ranking Module. The results suggest that the Automated Question generation system produces an optimally ranked list of relevant questions for Genesis. Mon, 01 Apr 2019 00:00:00 GMT https://hdl.handle.net/1721.1/121129 2019-04-01T00:00:00Z https://hdl.handle.net/1721.1/119668 Learning by Asking Questions and Learning by Aligning Stories: How a Story-Grounded Problem Solver can Acquire Knowledge Yang, Zhutian; Winston, Patrick Henry We describe how a problem solver, grounded in the Genesis Story Understanding System, acquires knowledge by asking questions and by aligning successful problem-solving stories. To illustrate learning by asking questions, we demonstrate how the Genesis problem solver learns the steps to mix a blocks-world martini from another problem solver and how it learns to make a real-world fruit salad from a human. To illustrate learning by aligning stories, we demonstrate how our Genesis problem solver learns to replace a phone battery from two 80-word stories that have much irrelevant detail and nothing expressed in exactly the same way. We conclude that the Genesis problem solver learns much like humans do. It asks questions and exploits precedents. It learns something specific from each experience. It tells itself its own story as it solves problems, exhibiting a kind of self-aware behavior. This report has related videos that can be viewed online (see "has part" links below). Mon, 17 Dec 2018 00:00:00 GMT https://hdl.handle.net/1721.1/119668 2018-12-17T00:00:00Z https://hdl.handle.net/1721.1/119652 Self-Aware Problem Solving Winston, Patrick Henry I describe a problem-solving scenario in which the Genesis story understanding system tells its own story, in its own inner language, as it answers a question, ``Did Lu kill Shan because America is individualistic,'' about a grisly murder. Genesis's inner-language story enables Genesis to describe, in English, what it is doing as it answers questions, finds concepts in its own thinking, summarizes, instructs, and finds similar problem-solving stories. I suggest that the ideas in Genesis's self-awareness capability will lead to more trustworthy systems. Sun, 16 Dec 2018 00:00:00 GMT https://hdl.handle.net/1721.1/119652 2018-12-16T00:00:00Z https://hdl.handle.net/1721.1/119651 The Genesis Enterprise: Taking Artificial Intelligence to another Level via a Computational Account of Human Story Understanding Winston, Patrick Henry; Holmes, Dylan We propose to develop computational accounts of human intelligence and to take intelligent systems to another level using those computational accounts. To develop computational accounts of human intelligence, we believe we must develop biologically plausible models of human story understanding, and then use those models to implement story-understanding systems that embody computational imperatives. We illustrate our approach by describing the development of the Genesis Story Understanding System and by explaining how Genesis goes about understanding short, up to 100-sentence stories, expressed in English. The stories include, for example, summaries of plays, fairy tales, international conflicts, and Native American creation myths. Genesis answers questions, interprets with controllable allegiances and cultural biases, notes personality traits, anticipates trouble, measures conceptual similarity, aligns stories, reasons analogically, summarizes, tells persuasively, composes new stories, and performs story-grounded hypothetical reasoning. We explain how we ensure that work on Genesis is scientifically grounded; we identify representative questions to be answered by our Brain and Cognitive Science colleagues; and we note why story understanding has much to offer not only to Artificial Intelligence but also to fields such as business, economics, education, humanities, law, neuroscience, medicine, and politics. Sat, 15 Dec 2018 00:00:00 GMT https://hdl.handle.net/1721.1/119651 2018-12-15T00:00:00Z