Inspiration
We wanted to create an efficient and simple way to construct well-designed layouts for users using plain English.
What it does
It takes commands, such as "Draw a pink circle,” and fabricates the associated shapes, icons, and even gifs accordingly.
How we built it
A node.js server running the webpage takes input from the user and sends it to the Flask back end, which communicates with the Google Cloud ML NLP and wit.ai services to determine intents and entities for output.
Challenges we ran into
Getting Google Cloud ML NLP to work was rather difficult at first, but then we supplemented it with wit and it became a breeze.
Accomplishments that we're proud of
None of us had used Google Cloud Machine Learning services in Python before, so that was a fun learning curve.
What we learned
We gained a lot of insight regarding natural language processing and the integration of voice recognition.
What's next for ARTiculate
In the future, we hope to implement more entities and intents for input to support different types of objects.
Log in or sign up for Devpost to join the conversation.