With Luis von Ahn’s reCAPTCHA, users help correct distorted words in digitized books.
What’s the News: Nothing…yet! But word is that Luis von Ahn–the Carnegie Mellon professor behind the clever projects reCAPTCHA and ESP Game–is bringing his crowdsourcing know-how to bear on the problem of web translation. With Duolingo, a project his lab has been working on for the last year and a half, people learning new languages will serve as translators. How well will that work? It remains to be seen, but according to von Ahn, a private beta version should be launching in several weeks.
How the Heck: Getting good translations online is difficult; it generally requires a human being, and certainly isn’t free. von Ahn described his plan for making decent, free web translations possible to TechCrunch:
“The solution was to transform language translation into something that millions of people WANT to do, and that helps with the problem of lack of bilinguals: language education. It is estimated that there are over 1 billion people learning a foreign language. So, the site that we’ve been working on, Duolingo, will be a 100% free language learning site in which people learn by helping to translate the Web. That is, they learn by doing.
“We’re now mostly testing the site, and it really works — it teaches users a foreign language very well, and the combined translations that we get in return are as accurate as those from professional language translators,” he says. (via TechCrunch)
What’s the Context:
reCAPTCHA and ESP Game (now called Google Image Labeler) use crowdsourcing on problems that machine learning just can’t solve:
With reCAPTCHA, the distorted words you have to identify before making an online purchase, posting a comment, and so on are drawn from digitized books. Computer algorithms trying to correct glitches in the scanned text can’t tell what the words are, but humans can. So with each purchase, you’re helping books go online.
In ESP Game, users are presented with images to tag as part of a game. The result: when you search for images online, the results correspond to what you’re looking for.
The Future Holds: A private beta version, for starters: You can sign up to be notified on Duolingo’s progress here.
