Linguists are attempting to harness the power of crowdsourcing to help machines achieve perfect translations. Computer translators such as Babelfish and Google Translate work best when they have a lot of translation data to work from, says University of Maryland professor Philip Resnik. However, there are only a handful of languages, such as French and Chinese, which have enough data for these programs to produce an effective translation. Resnik and colleagues are developing ways to use crowdsourcing to enable human and computer translators to work together. They say the technology could be the key to translating hundreds of lesser-known languages.
Maryland professor Judith Klavans says today's world requires the need to understand a wide variety of languages. "If you can't figure them out quickly, then we don't know what's going on anywhere."
Resnik notes that the experiments with crowdsourcing are still in their early stages. "It's possible that crowdsourcing will not get us all the way to fully automatic, high-quality translation," he says. "But it can get us a lot closer, by bringing humans and machines closer together in a way that hasn't happened before."
From NPR Online
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA