A new company called Duolingo could be the future of foreign language translation according to MIT Technology Review. Co-created by Luis Von Ahn, a computer science professor at Carnegie Mellon University, Duolingo harnesses the effort of language learners all over the world to create a language translation engine that is as good as professional services that charge up to twenty cents per word.
The company, which launched just this summer, has already attracted nearly $20 million in venture capital funding and offers free courses in English to speakers of Spanish and Portuguese and free lessons in Spanish, German, Portuguese and French to students who speak English. Since opening its virtual doors in June, Duolingo’s offerings have attracted more than 300,000 people each week.
The company is going up against popular language software such as Rosetta Stone (itself a less costly alternative to in-person lessons). But von Ahn thinks he has the edge, and not only because his classes are free.
“Most language-learning software providers have no incentive for you to learn,” he says. “Once [they] get your $500, they’re happy. We’ll do a lot to get you to come back, because it really matters.” His hoped-for translation business depends on it.
Keeping people coming back is what occupies the days of Duolingo’s 20 employees. Based in Pittsburgh, Pennsylvania, they are all working on improving the quality of language instruction offered on the company’s website. According to Von Ahn, currently about 30% of first-time Duolingo users are still visiting the website and taking lessons a week later. Although such a return rate might sound low for the average business, it’s impressive for a web-based service.
The fact that the program is customized to each student’s individual skill level is no doubt part of what keeps them coming back. The computer knows how to assess each learner’s progress, and then offer lessons that meet their individual needs. It can even offer guide on pronunciation based on how well or how poorly each student is performing.
Meanwhile, any learning that is going on is by no means one-sided. Just as students are slowly mastering a language thanks to the lessons offered by Duolingo, the computer engine that drives the system is improving its own translation skills.
The other side of the business comes in when students are asked to practice by translating single sentences from one language to another. Those sentences are currently taken from sites von Ahn thinks should be translated anyway, such as English Wikipedia articles without equivalents in Spanish. Multiple students translate the same sentence; software compares those results to settle on a final translation. After many sentences are put through this process, they are combined to create a translation of an entire document. The results, says von Ahn, are better than an automated translation but typically just short of professional quality.