Google’s translation fillip doesn’t come out of the blue. “It can be unsettling, but we've tested it in a lot of places and it just works,” he says. That independence makes it hard for even the system’s creators to understand what it’s doing, but the results speak for themselves, says Le. Instead, the software works out its own way to break up text into smaller fragments that often look nonsensical and don’t generally correspond to the phonemes of speech. It even reads and creates text without bothering with the concept of words. Google’s new system isn’t given a recipe and figures out its own path to reliably convert text from one language to another. It had components created to learn certain things, for example how to reorder the words in a sentence in different languages. But the old system was designed to use a particular recipe to translate text. Le says the impressive results came from Google’s researchers making their neural-network-powered translation system much more independent of its human designers.īoth the old and new systems learn to translate by looking at collections of documents that had been translated into different languages. In Google’s tests, humans scored the new system between 64 and 87 percent better than the previous one. The old system was not close to human performance. Google’s new system also scored close to human translators for French to English. For English to Spanish, Google’s new system scored 5.43 on average, not far off the 5.55 given to human translations. Participants used a scale from 0 to 6 to rate the fluency of translations of 500 sentences taken randomly from Wikipedia or news articles. When people fluent in two languages were asked to compare the work of Google’s new system against that of human translators, they sometimes couldn’t see much difference between them. Le says the latest results show that time has now come.Ī paper released by Google includes results from translating from English into Spanish, French, and Chinese, and from each of those languages into English. Since 2014, researchers at Google have been investigating how deep learning might also deliver a shot in the arm to translation.
0 kommentar(er)
