Experiment 4: Question Recognition

In this experiment Ditto the donkey is being trained to recognise questions.

The experiment is a simple example of supervised machine learning. Using a training set of examples of questions and other sayings, we're training Ditto to understand what a question "sounds like". At this early stage he's seen only a few examples, so we'd like you to help us by providing some more.

When Ditto receives a message from you, he tries to work out whether it's a question or not. He knows about "?" and "!" characters, so you could leave them out and see how good he is without them. For example, "How are you" and "What is that" are questions, but "How interesting" and "What nonsense" aren't. We hope his performance will improve as we increase the number of examples.

We select the training examples ourselves, and we teach Ditto away from the website. Therefore he won't learn instantly from things you say.

Ditto was last trained on 20 April 2007, using 1102 examples.

We're logging your messages and we'll use them as a source of training examples. However, you can't be identified as an individual, so feel free to say whatever you like. Please interact with Ditto and help him to learn!

More about supervised learning from Wikipedia