Google adds 20 languages to instant translation app

30 Jul 2015 | Author: | No comments yet »

Google Translate just got way better.

The search engine giant added 20 languages to their instant virtual translation app, a big leap from the original seven languages (English, French, German, Italian, Portuguese, Russian and Spanish) people could use to instantly identify words in a foreign language.

Available for both iOS and Android, Translate doesn’t just shuffle words and phrases from one language to another—it can also literally rewrite the world around you. TechCrunch reports that the app has recently expanded from translating seven languages to 27 languages, including Lithuanian, Norwegian, Polish, and Romanian.

Additionally, if a user takes a photo of the text through camera mode, Google can translate the text into an additional 10 languages, for a total of 37. Its most handy, and impressive, tool is the six-month-old instant translation feature, using the goodies from the acquired Word Lens, that lets you point your camera at something written in another language, say a sign, and it’ll translate into your language with ridiculous accuracy in almost real-time. Google’s secret to recognizing this vast array of languages is hidden in deep neural networks, the same networks that create hallucinative images and eerie art. TechCrunch spoke with Julie Cattiau, the product manager for Google GOOG 0.63% Translate, who said: Our mission is to help overcome language barriers.

By teaming up with Quest Visual, Google was “able to work with some of the top researchers in deep learning,” according to Google’s research blog. The images undergo a step-by-step process, which begins when the app finds letters in the image through identifying blocks of pixels with similar colors next to each other.

As TechCrunch’s Drew Olanoff explains, Google built this feature around Word Lens, a program that it acquired when it purchased Quest Visual last year. But part of that is also the overall user experience, which is why we also invest in things like instant camera translation and multi-language conversation. When I showed it a volume of Portuguese poetry, it was able to offer serviceable—if singularly unpoetic—takes on some lines. “The Martian found me on the street,” a Carlos Dumond de Andrade poem, aptly titled “Science Fiction,” promisingly begins, only to continue, “And had fear of my impossibility human.” Not bad, but I’ll stick with Richard Zenith’s more elegant rendering: “A Martian ran into me on the street/ and recoiled at my human impossibility.” While it was impressive to watch the words take shape on my phone’s screen, this clearly isn’t the sort of task that the program was designed to accomplish—and it shouldn’t be faulted for its failure.

Google Translate performed much better in my neighborhood coffee shop, successfully translating signs into Spanish, Filipino, and a variety of other languages, but it struggled to make sense of the specials scribbled on the chalkboard. I spoke to Julie Cattiau, product manager at Google Translate, yesterday about the Translate project as a whole, and asked specifically about Translate as an aid, rather than a replacement: JC: Translate is not a replacement for a language-learning course; it’s not going to teach you a language from scratch or all of the intricacies involved in learning a language. Like Google’s image recognition software—which has gotten the company into a bit of trouble in the recent past—Translate uses convolutional neural networks to determine what is and isn’t a letter, and then to guess how those letters fit together into words. For instance, a handwritten “s” could have been interpreted as a “5” in the translation process, but the program would still ultimately translate the mistaken “5uper” as “super.” But not everyone has a data processing center with the capabilities of Google. To counter that issue, Google had to develop a small neural net to limit the information density that the computer processor handles. “Sometimes new technology can seem very abstract, and it’s not always obvious what the applications for things like convolutional neural nets could be,” notes the Google research blog. “We think breaking down language barriers is one great use.” And Google promises that there more barriers to be broken: “More than half of the content on the Internet is in English, but only around 20% of the world’s population speaks English.

JC: Personally, I really enjoy reading and hearing user stories around how we were able to improve their lives by enabling them to connect with other people — whether it’s someone successfully ordering off of a foreign menu, a couple getting married who didn’t speak each other’s languages, or a life being saved because an emergency responder could communicate with someone.

Here you can write a commentary on the recording "Google adds 20 languages to instant translation app".

* Required fields
Our partners
Follow us
Contact us
Our contacts

ICQ: 423360519

About this site