Groups Similar Search Look up By Text Browse About

Google taps neural nets for better offline translation in 59 languages

Googles online translations have been powered by neural machine translation (NMT) since 2016, and today the company is rolling out its neural net-driven approach to more accurate, natural-sounding translations for Google Translate iOS and Android app users to carry out translations offline in 59 languages. Offline NMT was made by the Translate team in conjunction with the Google Brain team using TensorFlow, Google product manager Julie Cattiau told VentureBeat in a phone interview. Unlike for other Google apps, 95 percent of Google Translates user base is outside the United States, in countries like India, Brazil, and Indonesia, Cattiau said. So we hear a lot from our users that its great to have high quality online, but a lot of them are either unable to access an internet connection or they would prefer to save on their data plan. So we made it a priority over the past year and a half to basically squeeze our NMT models onto peoples devices, she said. Rather than the previous machine learning approach that provided interpretation by scanning phrases of a sentence, offline translations with NMT analyze entire chunks of text at once, allowing for more natural-sounding, grammatically sound, context-aware translations. When connected to the internet, Conversations mode in the Google Translate app can provide on-the-spot voice translation. However, NMT offline translation launches today with text-only translation; it does not extend to features in the Translate app that allow you to interpret the menu you take a picture of or translate peoples voices. Conversation mode in Pixel Buds, Googles first pair of earbuds, drew comparisons last fall to the Babel fish in Hitchhikers Guide to the Galaxy. In order to make real-time voice translation possible offline, Google will have to make other elements of AI that combine to enable Conversations mode available offline too, such as speech recognition and synthesis of words from text back into speech. Each of those parts needs to be built on-device for the full experience to work, and thats definitely something we want to launch, she said. Theres no date announced at the moment, but text translation is definitely one of the building blocks that will lead towards having an end-to-end offline translation for speech. No app update is necessary to get offline neural machine translations. Google Translate users who previously downloaded offline translation packages will see a banner encouraging them to click there for better translation, while Translate users new to offline translations will have to go into the app and select the languages they want to use offline. Each language package will take up roughly 35-45 MB, roughly equivalent in size to previous offline packages but higher quality. We cant run these very consuming models that requires a lot of computing power on $50 phones, so the trick with this launch was for engineers to squeeze the models and make them run on very low-end Android devices. That was the challenge of this launch, Cattiau said. User should notice a difference in quality from previous offline translations, but online translations will still be more accurate than offline translations, Cattiau said, as concessions were made to reduce language packages in size. Like the previously used phrase-based machine learning approach, NMT leverages hundreds of millions of example translations of things like articles, books, documents, and search results. Googles language prowess doesnt just improve its Translate app. The Alphabet subsidiary has committed to making Google Assistant available in more than 30 languages by the end of the year, a number that far surpasses Alexas four languages and Siris ability to speak 20 languages.

Google brings offline neural machine translations for 59 languages to its Translate app

Currently, when the Google Translate apps for iOS and Android has access to the internet, its translations are far superior to those it produces when its offline. Thats because the offline translations are phrase-based, meaning they use an older machine translation technique than the machine learning-powered systems in the cloud that the app has access to when its online. But thats changing today. Google is now rolling out offline Neural Machine Translation (NMT) support for 59 languages in the Translate apps. Today, only a small number of users will see the updated offline translations, but it will roll out to all users within the next few weeks. The list of supported languages consists of a wide range of languages. Because I dont want to play favorites, here is the full list: Afrikaans, Albanian, Arabic, Belarusian, Bengali, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian, Creole, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Jannada, Korean, Latvian, Lithuanian, Macedonian, Malay, Maltese, Marathi, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese and Welsh. In the past, running these deep learning models on a mobile device wasnt really an option since mobile phones didnt have the right hardware to efficiently run them. Now, thanks to both advances in hardware and software, thats less of an issue and Google, Microsoft and others have also found ways to compress these models to a manageable size. In Googles case, thats about 30 to 40 megabytes per language. Its worth noting that Microsoft also announced a similar feature for its Translator app earlier this year. It uses a very similar technique, but for the time being, it only supports about a dozen languages.