HowTo is an interpreter which takes a block of text, which we call a story, and converts it to a semi-textual, semi-visual representation. Inspired by the inefficiency of long convoluted instructions, we sought to create something that allows maximum productivity by transforming the dauntingly complex into simple, user-friendly guides. Powered by the Stanford Parser, HowTo is able to dissect a story and tag each word by assigning it its respective part of speech. Through this process, HowTo recognizes the essential part of each sentence in order to provide the user with a concise visual version of the story.
Although HowTo is geared toward simplifying instructions, the idea behind it is limitless. Word-to-visual transformation is an invaluable idea that can be extended to fields such as education, medicine, business, and intelligent services. Students could input their notes and receive diagrams, pictures, and flowcharts to aid them in their studies. Doctor/patient relationships can extend from the hospital as a doctor can create a patient’s blood diagram by simply typing a paragraph. Presentations can be constructed from a text document, boosting a business’ efficiency by eradicating the tedious process of dragging and dropping images around in PowerPoint. It could even be used to extract terrorist threats from social media. Pair this idea with a machine-learning algorithm and the impact will be astounding.