Jennifer Lissette Madiedo

Jennifer Lissette Madiedo
MIT EECS | Fairbairn Undergraduate Research and Innovation Scholar
Advisor: Patrick H. Winston
Department: EECS
Years: 2018-2019
Research Project Title:

Identification and Synthesis of Repetitive Structures for Persuasion

abstract:Genesis is an AI system that understands, tells, and composes stories using common sense rules and higher-level concept patterns. One area where Genesis still needs development is in persuasion. Currently, it can persuade readers towards a certain point of view via a technique of information removal. The goal of my project is to achieve persuasion through synthesis of new text to be inserted into the story. Focusing specifically on persuasion through repetitive structures, Genesis will be able to read a story and decide which words or phrases to create, and where to insert them, to attempt to persuade the reader of a certain idea. The success of this project represents a higher level of understanding achieved by Genesis, and another step closer to teaching computers to think as humans do.

I am participating in SuperUROP because my past research with the Personal Robotics Group in the Media Lab piqued my interest in how children learn new ideas, and how we can use those same methods to teach programs to learn on their own. I aim to get experience on a long-term research project in my field of interest, and learn more about the applications and ethics of intelligent programs