Google Data » Google Translate

Zero-Shot Translation with Google’s Multilingual Neural Machine Translation System

Research Blog — Tue, 22 Nov 2016 18:00:00 +0000

Posted by Mike Schuster (Google Brain Team), Melvin Johnson (Google Translate) and Nikhil Thorat (Google Brain Team)

In the last 10 years, Google Translate has grown from supporting just a few languages to 103, translating over 140 billion words every day. To make this possible, we needed to build and maintain many different systems in order to translate between any two languages, incurring significant computational cost. With neural networks reforming many fields, we were convinced we could raise the translation quality further, but doing so would mean rethinking the technology behind Google Translate.

In September, we announced that Google Translate is switching to a new system called Google Neural Machine Translation (GNMT), an end-to-end learning framework that learns from millions of examples, and provided significant improvements in translation quality. However, while switching to GNMT improved the quality for the languages we tested it on, scaling up to all the 103 supported languages presented a significant challenge.

In “Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation”, we address this challenge by extending our previous GNMT system, allowing for a single system to translate between multiple languages. Our proposed architecture requires no change in the base GNMT system, but instead uses an additional “token” at the beginning of the input sentence to specify the required target language to translate to. In addition to improving translation quality, our method also enables “Zero-Shot Translation” — translation between language pairs never seen explicitly by the system.

Here’s how it works. Let’s say we train a multilingual system with Japanese⇄English and Korean⇄English examples, shown by the solid blue lines in the animation. Our multilingual system, with the same size as a single GNMT system, shares its parameters to translate between these four different language pairs. This sharing enables the system to transfer the “translation knowledge” from one language pair to the others. This transfer learning and the need to translate between multiple languages forces the system to better use its modeling power.

This inspired us to ask the following question: Can we translate between a language pair which the system has never seen before? An example of this would be translations between Korean and Japanese where Korean⇄Japanese examples were not shown to the system. Impressively, the answer is yes — it can generate reasonable Korean⇄Japanese translations, even though it has never been taught to do so. We call this “zero-shot” translation, shown by the yellow dotted lines in the animation. To the best of our knowledge, this is the first time this type of transfer learning has worked in Machine Translation.

The success of the zero-shot translation raises another important question: Is the system learning a common representation in which sentences with the same meaning are represented in similar ways regardless of language — i.e. an “interlingua”? Using a 3-dimensional representation of internal network data, we were able to take a peek into the system as it translates a set of sentences between all possible pairs of the Japanese, Korean, and English languages.

Part (a) from the figure above shows an overall geometry of these translations. The points in this view are colored by the meaning; a sentence translated from English to Korean with the same meaning as a sentence translated from Japanese to English share the same color. From this view we can see distinct groupings of points, each with their own color. Part (b) zooms in to one of the groups, and part (c) colors by the source language. Within a single group, we see a sentence with the same meaning but from three different languages. This means the network must be encoding something about the semantics of the sentence rather than simply memorizing phrase-to-phrase translations. We interpret this as a sign of existence of an interlingua in the network.

We show many more results and analyses in our paper, and hope that its findings are not only interesting for machine learning or machine translation researchers but also to linguists and others who are interested in how multiple languages can be processed by machines using a single system.

Finally, the described Multilingual Google Neural Machine Translation system is running in production today for all Google Translate users. Multilingual systems are currently used to serve 10 of the recently launched 16 language pairs, resulting in improved quality and a simplified production architecture.

A Neural Network for Machine Translation, at Production Scale

Research Blog — Tue, 27 Sep 2016 17:00:00 +0000

Posted by Quoc V. Le & Mike Schuster, Research Scientists, Google Brain Team

Ten years ago, we announced the launch of Google Translate, together with the use of Phrase-Based Machine Translation as the key algorithm behind this service. Since then, rapid advances in machine intelligence have improved our speech recognition and image recognition capabilities, but improving machine translation remains a challenging goal.

Today we announce the Google Neural Machine Translation system (GNMT), which utilizes state-of-the-art training techniques to achieve the largest improvements to date for machine translation quality. Our full research results are described in a new technical report we are releasing today: “Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation” [1].

A few years ago we started using Recurrent Neural Networks (RNNs) to directly learn the mapping between an input sequence (e.g. a sentence in one language) to an output sequence (that same sentence in another language) [2]. Whereas Phrase-Based Machine Translation (PBMT) breaks an input sentence into words and phrases to be translated largely independently, Neural Machine Translation (NMT) considers the entire input sentence as a unit for translation.The advantage of this approach is that it requires fewer engineering design choices than previous Phrase-Based translation systems. When it first came out, NMT showed equivalent accuracy with existing Phrase-Based translation systems on modest-sized public benchmark data sets.

Since then, researchers have proposed many techniques to improve NMT, including work on handling rare words by mimicking an external alignment model [3], using attention to align input words and output words [4] and breaking words into smaller units to cope with rare words [5,6]. Despite these improvements, NMT wasn't fast or accurate enough to be used in a production system, such as Google Translate. Our new paper [1] describes how we overcame the many challenges to make NMT work on very large data sets and built a system that is sufficiently fast and accurate enough to provide better translations for Google’s users and services.

Data from side-by-side evaluations, where human raters compare the quality of translations for a given source sentence. Scores range from 0 to 6, with 0 meaning “completely nonsense translation”, and 6 meaning “perfect translation."

The following visualization shows the progression of GNMT as it translates a Chinese sentence to English. First, the network encodes the Chinese words as a list of vectors, where each vector represents the meaning of all words read so far (“Encoder”). Once the entire sentence is read, the decoder begins, generating the English sentence one word at a time (“Decoder”). To generate the translated word at each step, the decoder pays attention to a weighted distribution over the encoded Chinese vectors most relevant to generate the English word (“Attention”; the blue link transparency represents how much the decoder pays attention to an encoded word).

Using human-rated side-by-side comparison as a metric, the GNMT system produces translations that are vastly improved compared to the previous phrase-based production system. GNMT reduces translation errors by more than 55%-85% on several major language pairs measured on sampled sentences from Wikipedia and news websites with the help of bilingual human raters.

An example of a translation produced by our system for an input sentence sampled from a news site. Go here for more examples of translations for input sentences sampled randomly from news sites and books.

In addition to releasing this research paper today, we are announcing the launch of GNMT in production on a notoriously difficult language pair: Chinese to English. The Google Translate mobile and web apps are now using GNMT for 100% of machine translations from Chinese to English—about 18 million translations per day. The production deployment of GNMT was made possible by use of our publicly available machine learning toolkit TensorFlow and our Tensor Processing Units (TPUs), which provide sufficient computational power to deploy these powerful GNMT models while meeting the stringent latency requirements of the Google Translate product. Translating from Chinese to English is one of the more than 10,000 language pairs supported by Google Translate, and we will be working to roll out GNMT to many more of these over the coming months.

Machine translation is by no means solved. GNMT can still make significant errors that a human translator would never make, like dropping words and mistranslating proper names or rare terms, and translating sentences in isolation rather than considering the context of the paragraph or page. There is still a lot of work we can do to serve our users better. However, GNMT represents a significant milestone. We would like to celebrate it with the many researchers and engineers—both within Google and the wider community—who have contributed to this direction of research in the past few years.

Acknowledgements:
We thank members of the Google Brain team and the Google Translate team for the help with the project. We thank Nikhil Thorat and the Big Picture team for the visualization.

References:
[1] Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Łukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, Jeffrey Dean. Technical Report, 2016.
[2] Sequence to Sequence Learning with Neural Networks, Ilya Sutskever, Oriol Vinyals, Quoc V. Le. Advances in Neural Information Processing Systems, 2014.
[3] Addressing the rare word problem in neural machine translation, Minh-Thang Luong, Ilya Sutskever, Quoc V. Le, Oriol Vinyals, and Wojciech Zaremba. Proceedings of the 53th Annual Meeting of the Association for Computational Linguistics, 2015.
[4] Neural Machine Translation by Jointly Learning to Align and Translate, Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio. International Conference on Learning Representations, 2015.
[5] Japanese and Korean voice search, Mike Schuster, and Kaisuke Nakajima. IEEE International Conference on Acoustics, Speech and Signal Processing, 2012.
[6] Neural Machine Translation of Rare Words with Subword Units, Rico Sennrich, Barry Haddow, Alexandra Birch. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016.

Translate where you need it: in any app, offline, and wherever you see Chinese

Google Blogs — Wed, 11 May 2016 15:00:00 +0000

Of the 500 million+ people who use Google Translate, more than 9 in 10 live outside the U.S. We've talked with thousands of you in India, Indonesia, Brazil, and Thailand to learn what works and what doesn’t—and today we’re rolling out some big improvements.

First, say hello to Tap to Translate on Android. We know millions of you painstakingly copy-paste text between Google Translate and other apps. Now, you can just copy the text of a chat, comment, song lyric, etc. in whichever app you’re using, and a translation will pop up right there—no need to switch apps:

Watch the video to learn more. Tap to Translate works for all 103 of Google Translate’s languages on any Android phone running Jellybean (4.2) and above.

Next, Offline Mode now works on iOS, and joins Android in using small offline packages. We know that many of you found the previous packages too big to download on unreliable data connections or to keep on your phone’s limited storage. That’s why we shrunk them by 90 percent, to a much more manageable 25 MB each.

Offline Mode is easy to set up: Just tap the arrow next to the language name to download the package for that language, and then you’ll be ready to do text translations whether you’re online or not—and it works with Tap to Translate too. We’ve just added a Filipino language pack, bringing our total number of offline languages to 52.

Finally, we’re adding Word Lens in Chinese. It’s our 29th language for instant visual translation, and it reads both to and from English, for both Simplified and Traditional Chinese. Try it on menus, signs, packages, and other printed text. As with all Word Lens languages, it works offline.

With Tap to Translate, improved Offline Mode, and Word Lens in Chinese, we hope you’ll find the latest version of Google Translate a helpful companion. These updates are rolling out over the next few days.

Posted by Barak Turovsky, Product Lead, Google Translate

Ten years of Google Translate

Google Translate Official Blogger — Thu, 28 Apr 2016 13:04:00 +0000

Ten years ago, we launched Google Translate. Our goal was to break language barriers and to make the world more accessible. Since then we’ve grown from supporting two languages to 103, and from hundreds of users to hundreds of millions. And just like anyone’s first 10 years, we’ve learned to see and understand, talk, listen, have a conversation, write, and lean on friends for help.

But what we're most inspired by is how Google Translate connects people in communities around the world, in ways we never could have imagined—like two farmers with a shared passion for tomato farming, a couple discovering they're pregnant in a foreign country, and a young immigrant on his way to soccer stardom.

Here’s a look at Google Translate today, 10 years in:

1. Google Translate helps people make connections.
Translate can help people help each other, often in the most difficult of times. Recently we visited a community in Canada that is using Translate to break down barriers and make a refugee family feel more welcome:

2. There are more than 500 million of you using Google Translate.
The most common translations are between English and Spanish, Arabic, Russian, Portuguese and Indonesian.

3. Together we translate more than 100 billion words a day.

4. Translations reflect trends and events.
In addition to common phrases like “I love you,” we also see people looking for translations related to current events and trends. For instance, last year we saw a big spike in translations for the word "selfie,” and this past week, translations for "purple rain" spiked by more than 25,000 percent.

5. You’re helping to make Google Translate better with Translate Community.
So far, 3.5 million people have made 90 million contributions through Translate Community, helping us improve and add new languages to Google Translate. A few properly translated sentences can make a huge difference when faced with a foreign language or country. By reviewing, validating and recommending translations, we’re able to improve the Google Translate on a daily basis.

6. Brazil uses Google Translate more than any other country.
Ninety-two percent of our translations come from outside of the United States, with Brazil topping the list.

7. You can see the world in your language.
Word Lens is your friend when reading menus, street signs and more. This feature in the Google Translate App lets you instantly see translations in 28 languages.

8. You can have a conversation no matter what language you speak.
In 2011, we first introduced the ability to have a bilingual conversation on Google Translate. The app will recognize which language is being spoken when you’re talking with someone, allowing you to have a natural conversation in 32 languages.

9. You don't need an Internet connection to connect.
Many countries don’t have reliable Internet, so it’s important to be able to translate on the go. You can instantly translate signs and menus offline with Word Lens on both Android and iOS, and translate typed text offline with Android.

10. There's always more to translate.
We’re excited and proud of what we’ve accomplished together over the last 10 years—but there’s lots more to do to break language barriers and help people communicate no matter where they’re from or what language they speak. Thank you for using Google Translate—here’s to another 10!

Posted by Barak Turovsky, Product Lead, Google Translate

Translate Community, and Sietske Poepjes, help add Frisian to Google Translate

Google Translate Official Blogger — Fri, 26 Feb 2016 17:35:00 +0000

Last week, we introduced 13 new languages to Google Translate. As we mentioned, there are a number of factors that go into adding a new language: once it’s established that it’s a written language with a significant amount of translations available on the web, we use a combination of machine learning, licensed content and input from Translate Community. One language where Translate Community played an especially big role was Frisian.

Today, we’re speaking with Sietske Poepjes, a member of the Frisian community who recently helped to organize a Translate Community event. Thanks to Sietske and the community's support, we were able to get enough data to officially add Frisian to Google Translate. The interview gives an overview of what went into Sietske’s community effort and how you can get involved.

What’s your job and title? I'm a provincial deputy on language and education in the province of Fryslân. Fryslân is one of the twelve provinces in The Netherlands. It’s the only province with an official language other than Dutch, namely: Frisian.

Sietske Poepjes

Why is it important to add the Frisian language to Google Translate? Frisian is the second official language in the Netherlands and is the mother language of more than half of the population of the province of Fryslân. Most people in Fryslân are able to understand or speak the language, but not a lot of people are able to write it at a high level (only 15%). With most of our education taking place in Dutch, Google Translate can be used as a tool for those who can’t write the Frisian language sufficiently.

Besides, it’s important for lesser used languages like Frisian to be used digitally. Being one of the languages in Google Translate also enhances the visibility of the language and allows people throughout the world to translate to and from the language.

So you organized Frisian Google Translate Week last year -- what motivated you to organize the event?To add Frisian to Google Translate, we knew we needed a lot of data. Since there wasn’t sufficient material available both in the Frisian and English language, Translate Community could help. To get everyone involved, the province of Fryslân decided to organise a central week in which everyone is asked to participate. The idea was that working together in the same week, we would motivate people to contribute even more. This has definitely paid out; thousands of people participated, resulting in nearly a million translated words!

Translate Community event.

How did you set up the event? Who did you work with?As the province of Fryslân, we coordinated the event with educational and scientific organisations and libraries, and received lots of support. The organisations invited employees, members, students or other interested people to come along and translate with them on a certain day/time. This turned out to work really well. One example: the Frisian department of the University of Groningen (which is outside of Fryslân) organised a reunion with former students and teachers and together they translated thousands of words.

We also organised an opening session which was the official start of the entire week and invited school children to help open the festival with their own song. At this opening session an introduction to Google Translate presentation was given by a Google Netherlands representative.

We provided hand-outs and made a training video on YouTube to guide people on how to navigate on Translate Community site and make contributions. We also created a commercial video (with famous Frisians), broadcast on the regional television “Omrop Fryslân”, which turned out to be very influential.

How did you motivate the participants?We relied on social media. We created our own Facebook event for people to join and asked all of the organisations involved to use their own social media to share our messages and calls for everyone to contribute. Participants could make a screenshot showing their number of contributions made, to share on Facebook. We gave the participant with the most contributions a Google Translate cake.

How did the Frisian week go? Any memorable moments?
The Frisian Google Translate Week became a huge success. A lot of Frisians participated, resulting in a whopping one million translated words at the end of the week. The total number of translations was revealed at a national festival for languages. It was amazing to see the amount of publicity we gained and to see that so many people were interested in our event. It was even broadcast in the Dutch news at prime time.

What’s the impact of the event? What are people’s reactions?
We saw the need for Google Translate, as we received a lot of feedback and questions from people who wanted to know when Frisian would be available in Google Translate.

The most impressive thing of the whole Frisian Google Translate Week is the commitment of all Frisians (in and outside the province of Fryslân). So many people participated and everyone felt the need to join and start translating. The Frisian community worked together to achieve a goal.

Have you worked on any follow up efforts?
Yes! We have organized a validation session. In this session, we have reached Frisian experts and gathered in the local provincial library to work together on validating the translations. It worked out really well, again the sense of community was very strong. And to thank everyone who participated in the Frisian Google Translate Week and the validation session, we organized a celebration party. It was a really nice party with a spectacular multilingual musical performance from the Frisian band ‘De Kast’. Their number-1 hit “De nije dei” (The new day) was performed with the lyrics in Dutch translated by Google Translate in the background. There were also secondary school pupils showing the use and work of Frisian in Google Translate to all guests.

The band De Kast, who performed songs in Frisian, Dutch and English with the meaning shown in other languages on the screen through Translate.

Any advice for future event organizers?
We think it is very important to communicate about the value of Google Translate for the language, it improves the visibility of the language, and it offers speakers of the language a very helpful and easy-to-use digital tool. It shows the vitality of the language, which is especially important for small languages such as Frisian. Second, we think it is important to cooperate with the local organisations for a sense of community. And last but not least: we have made a nice event of it. It was great fun!

If you would like to help improve Google Translate and organize Translate Community events for your language, apply here.

Posted by Mengmeng Niu, Program Manager, Google Translate

From Amharic to Xhosa, introducing Translate in 13 new languages — now over 100 in total!

Google Translate Official Blogger — Wed, 17 Feb 2016 14:09:00 +0000

In 2006, we started with machine learning-based translations between English and Arabic, Chinese and Russian. Almost 10 years later, with today’s update, we now offer 103 languages that cover 99% of the online population.

The 13 new languages — Amharic, Corsican, Frisian, Kyrgyz, Hawaiian, Kurdish (Kurmanji), Luxembourgish, Samoan, Scots Gaelic, Shona, Sindhi, Pashto and Xhosa — help bring a combined 120 million new people to the billions who can already communicate with Translate all over the world.

So what goes into adding a new language? Beyond the basic criteria that it must be a written language, we also need a significant amount of translations in the new language to be available on the web. From there, we use a combination of machine learning, licensed content and Translate Community.

As we scan the Web for billions of already translated texts, we use machine learning to identify statistical patterns at enormous scale, so our machines can "learn" the language. But, as already existing documents can’t cover the breadth of a language, we also rely on people like you in Translate Community to help improve current Google Translate languages and add new ones, like Frisian and Kyrgyz. So far, over 3 million people have contributed approximately 200 million translated words.

Before you dive into translating, here are a few fun facts about the new languages:

Amharic (Ethiopia) is the second most widely spoken Semitic language after Arabic
Corsican (Island of Corsica, France) is closely related to Italian and was Napoleon's first language
Frisian (Netherlands and Germany) is the native language of over half the inhabitants of the Friesland province of the Netherlands
Kyrgyz (Kyrgyzstan) is the language of the Epic of Manas, which is 20x longer than the Iliad and the Odyssey put together
Hawaiian (Hawaii) has lent several words to the English language, such as ukulele and wiki
Kurdish (Kurmanji) (Turkey, Iraq, Iran and Syria) is written with Latin letters while the others two varieties of Kurdish are written with Arabic script
Luxembourgish (Luxembourg) completes the list of official EU languages Translate covers
Samoan (Samoa and American Samoa) is written using only 14 letters
Scots Gaelic (Scottish highlands, UK) was introduced by Irish settlers in the 4th century AD
Shona (Zimbabwe) is the most widely spoken of the hundreds of languages in the Bantu family
Sindhi (Pakistan and India) was the native language of Muhammad Ali Jinnah, the "Father of the Nation” of Pakistan
Pashto (Afghanistan and Pakistan) is written in Perso-Arabic script with an additional 12 letters, for a total of 44
Xhosa (South Africa) is the second most common native language in the country after Afrikaans and features three kinds of clicks, represented by the letters x, q and c

We’ve come a long way with over 100 languages, but we aren’t done yet. If you want to help, International Mother Language day — just around the corner on February 21 — is a great time to get involved in Translate Community. To start, just select the languages you speak; then choose to either translate phrases on your own or validate existing translations. Every contribution helps improve the quality of translation over time. You can also share feedback directly from Translate.Google.com, so as you try out the new languages, we’d love to hear your suggestions.

For each new language, we make our translations better over time, both by improving our algorithms and systems and by learning from your translations with Translate Community. Today's update will be rolling out over the coming days.

No matter what language you speak, we hope today’s update makes it easier to communicate with millions of new friends and break language barriers one conversation at a time.

Posted by Sveta Kelman, Senior Program Manager, Google Translate

Translate Community: Over one million people and 50 million contributions

Google Translate Official Blogger — Mon, 28 Dec 2015 16:43:00 +0000

Over the past year, more than one million people speaking 117 languages have made 50 million contributions through the Google Translate Community.

With those contributions we’ve launched 10 new languages, including Chichewa (Chinyanja) and Malayalam (മലയാളം), and been able to make improvements in how we speak dozens of other languages. Now almost 50% of the most common phrases typed in Google Translate come from translations provided by the Translate Community.

Translate Community members come from all over the world and translate in many different ways - from translating on their own to hosting group events. This year, Bengali speakers worked together to host events throughout the country by partnering with schools and cultural groups. And Frisian speakers worked with their government to create a week of events dedicated to getting their language added to Google Translate.

This month, language lovers are participating in a Translatathon in India. With just a few more days to go, if you speak Hindi, Bengali, Telugu, Marathi, Tamil, Gujarati, Kannada, Malayalam or Punjabi, sign up today to help Google Translate deliver better translations in your community.

Posted by Mengmeng Niu, Translate Community Program Manager

India’s second Translatathon needs you!

Google Translate Official Blogger — Tue, 22 Dec 2015 23:43:00 +0000

Sometimes language isn’t straightforward. Only a Hindi speaker could tell you that although ऊँट के मुँह में जीरा may literally mean ‘cumin seed in a camel's mouth’, it actually means ‘a drop in the ocean’ or something too insufficient to fulfill a need.

There are 22 official languages in India. And while Google Translate can help you with nine of them at the moment, languages that are under-represented on the Internet like Bengali, Telugu, and Tamil could use a little help. This is where people who are passionate about their native languages can use the Translate Community tool to make a big difference.

We’ve just kicked off our second translatathon in India, this time for nine languages — Hindi, Bengali, Telugu, Marathi, Tamil, Gujarati, Kannada, Malayalam and Punjabi. You can use Google Translate Community on your phone, laptop or computer. Just type, swipe or tap translations in the languages you speak. You have the option to either translate phrases directly, or validate existing translations.

Last year 20,000 people contributed over one million new Hindi translations, helping improve the overall quality of Hindi content online. We’re now including all the Indic languages that Google Translate is available in, and we look forward to seeing how people from around the world can help Google say जंगल में मोर नाचा किस ने देखा? or আপনার পায়ে কুড়ল মারা more accurately. Millions of people in India are coming online for the first time and most of them don’t speak English. Bringing more Indian language content online, and improving Indian language translation quality, will help them have a better experience on the Web.

Validate phrases with the Google Translate Community tool

Once you join the translatathon, you can Translate and validate words and short phrases up until December 30. We will then reward the 50 most active and accurate contributors with an Android One phone*.

So why not stop by and say नमस्ते, নমস্কার, வணக்கம் and help India showcase the beauty and diversity of languages online. Register and participate at g.co/translatathon and thanks in advance for your help. You’re making the web better for everyone.

*Terms and conditions apply: https://goo.gl/kEAehI

Posted by Barak Turovsky, Product Lead, Google Translate

Fútbol, translated

Google Translate Official Blogger — Mon, 19 Oct 2015 16:20:00 +0000

We’re always amazed by the power of technology to connect people. Not long ago we heard a story involving the Google Translate app and a boy named Alberto who had recently moved from Spain to a small town in Northern Ireland, with little knowledge of English. When Alberto joined Portadown’s youth soccer club, his coaches Gary and Glen turned to Google Translate to communicate with Alberto and his mother, on and off the field. As they progressed from protección de la pelota to retroceso de bicicleta, Alberto grew to feel a part of the team. We loved this story (and wanted to share it with you) because what Gary and Glen did was so much bigger than translating sentences from one language into another. They didn’t just find a way to coach Alberto in football—they found a way to invite someone who was on the outside into their community.

¡Vamos, Alberto!

Posted by Barak Turovsky, Product Lead, Google Translate

Two new Translate features coming your way

Google Translate Official Blogger — Wed, 14 Oct 2015 15:43:00 +0000

We’re all about breaking language barriers, whatever language you speak or device you use. So with that in mind, over the next week, we’ll be rolling out two new Google Translate app features— instantly translating both English and German to Arabic and easier multitasking for iPad users.

See the world in a new language with instant visual translation
You can already have bilingual conversations from English or German to Arabic thanks to the conversation mode or text input in the Google Translate app. Today, we’re also adding the ability to translate printed text instantly between these languages.

To use instant visual translation, just open the app, click on the camera, and point it at the text you need to translate. You’ll see the text transform from one language to another in real-time on your screen. And the best part? There’s no Internet connection or cell phone data needed.

To try out Arabic with either English or German you'll be prompted to download a small (~2 MB) language pack.

Split View translations with the newest iPads
Starting today, customers using iPads supporting Split View will be able to use Google Translate along with the new feature. So if you’re sending an email or text and need to translate, you can see both apps at the same time. And it even works with text from online books or websites.

Whether you’re starting a new bi-lingual conversation on your iPad or using instant visual translation to find your way, Google Translate helps you see the world in your language. With today’s updates, we hope that we’re able to continue to help and give more translation options to the 500 million people using Google Translate to see over 100 billion words a day in their language.

Posted by Barak Turovsky, Product Lead, Google Translate

Translate text within apps thanks to the latest Android update

Google Translate Official Blogger — Tue, 06 Oct 2015 16:46:00 +0000

We face communication barriers every day. Switching back and forth between apps and screens to translate shouldn’t be another one. We’ve heard your feedback, and have worked with the Android team to make translating text, chats, and other app content a whole lot easier.

Beginning this week, you’ll be able to translate in 90 languages right from within some of your favorite apps like TripAdvisor, WhatsApp and LinkedIn.

Translating a TripAdvisor review from Portuguese

Composing a WhatsApp message in Russian

This update works on any device running the newest version of Android’s operating system (Android 6.0, Marshmallow). To get started, you first need to have the Translate app downloaded on your Android phone. From there, just go to an app, like TripAdvisor or LinkedIn, and highlight and select the text you want to translate. This feature is already enabled in apps that use Android text selection behavior. Developers who created custom text selection behavior can also easily add the new feature.

More than 500 million people translate over 100 billion words a day on Google Translate. With updates like this one, plus features like conversation mode and instant camera translation, we’re making Translate available anywhere you need it. So when you’re chatting with a new colleague from halfway around the world, conversation mode is perfect. Wondering which subway sign says “exit” on your next global adventure? Instant camera translation has your back. And now, when you’re sending messages or checking out reviews on your phone, you can translate right from within the apps you’re using.

Posted by Barak Turovsky, Product Lead, Google Translate

Watch your language! 44 of them, actually.

Google Translate Official Blogger — Thu, 20 Aug 2015 16:31:00 +0000

More than 500 million people use Google Translate every month across web and mobile phones, translating more than 100 billion words every day around the globe. Now, we’re launching Google Translate on all Android Wear watches, too.

Translate is built into the latest Android Wear software update, so you can have bilingual conversations even if you don’t have Google Translate on your phone, or if you’re away from your phone but connected via Wi-Fi.

And it’s easy to use - just speak into your watch to see your conversation translated into any of 44 languages. Flip your wrist to show the translation to a friend. When they respond in their own language, flip your wrist back, and you’ll see in your language what they’ve just said. Google Translate will automatically recognize which of the two languages is being spoken, so once you tap to start the conversation, all you and your buddy need to do is keep talking naturally.

Google Translate covers 90 languages total (for text translation), and we are always working to expand the number of languages that work across various features.

Posted by Barak Turovsky, Product Lead, Google Translate and Nathan Beach, Product Manager, Android Wear

How Google Translate squeezes deep learning onto a phone

Google Translate Official Blogger — Wed, 29 Jul 2015 22:48:00 +0000

Today we announced that the Google Translate app now does real-time visual translation of 20 more languages. So the next time you’re in Prague and can’t read a menu, we’ve got your back. But how are we able to recognize these new languages?

In short: deep neural nets. When the Word Lens team joined Google, we were excited for the opportunity to work with some of the leading researchers in deep learning. Neural nets have gotten a lot of attention in the last few years because they’ve set all kinds of records in image recognition. Five years ago, if you gave a computer an image of a cat or a dog, it had trouble telling which was which. Thanks to convolutional neural networks, not only can computers tell the difference between cats and dogs, they can even recognize different breeds of dogs. Yes, they’re good for more than just trippy art—if you're translating a foreign menu or sign with the latest version of Google's Translate app, you're now using a deep neural net. And the amazing part is it can all work on your phone, without an Internet connection. Here’s how.

Step by step
First, when a camera image comes in, the Google Translate app has to find the letters in the picture. It needs to weed out background objects like trees or cars, and pick up on the words we want translated. It looks at blobs of pixels that have similar color to each other that are also near other similar blobs of pixels. Those are possibly letters, and if they’re near each other, that makes a continuous line we should read.

Second, Translate has to recognize what each letter actually is. This is where deep learning comes in. We use a convolutional neural network, training it on letters and non-letters so it can learn what different letters look like.

But interestingly, if we train just on very “clean”-looking letters, we risk not understanding what real-life letters look like. Letters out in the real world are marred by reflections, dirt, smudges, and all kinds of weirdness. So we built our letter generator to create all kinds of fake “dirt” to convincingly mimic the noisiness of the real world—fake reflections, fake smudges, fake weirdness all around.

Why not just train on real-life photos of letters? Well, it’s tough to find enough examples in all the languages we need, and it’s harder to maintain the fine control over what examples we use when we’re aiming to train a really efficient, compact neural network. So it’s more effective to simulate the dirt.

Some of the “dirty” letters we use for training. Dirt, highlights, and rotation, but not too much because we don’t want to confuse our neural net.

The third step is to take those recognized letters, and look them up in a dictionary to get translations. Since every previous step could have failed in some way, the dictionary lookup needs to be approximate. That way, if we read an ‘S’ as a ‘5’, we’ll still be able to find the word ‘5uper’.

Finally, we render the translation on top of the original words in the same style as the original. We can do this because we’ve already found and read the letters in the image, so we know exactly where they are. We can look at the colors surrounding the letters and use that to erase the original letters. And then we can draw the translation on top using the original foreground color.

Crunching it down for mobile
Now, if we could do this visual translation in our data centers, it wouldn’t be too hard. But a lot of our users, especially those getting online for the very first time, have slow or intermittent network connections and smartphones starved for computing power. These low-end phones can be about 50 times slower than a good laptop—and a good laptop is already much slower than the data centers that typically run our image recognition systems. So how do we get visual translation on these phones, with no connection to the cloud, translating in real-time as the camera moves around?

We needed to develop a very small neural net, and put severe limits on how much we tried to teach it—in essence, put an upper bound on the density of information it handles. The challenge here was in creating the most effective training data. Since we’re generating our own training data, we put a lot of effort into including just the right data and nothing more. For instance, we want to be able to recognize a letter with a small amount of rotation, but not too much. If we overdo the rotation, the neural network will use too much of its information density on unimportant things. So we put effort into making tools that would give us a fast iteration time and good visualizations. Inside of a few minutes, we can change the algorithms for generating training data, generate it, retrain, and visualize. From there we can look at what kind of letters are failing and why. At one point, we were warping our training data too much, and ‘$’ started to be recognized as ‘S’. We were able to quickly identify that and adjust the warping parameters to fix the problem. It was like trying to paint a picture of letters that you’d see in real life with all their imperfections painted just perfectly.

To achieve real-time, we also heavily optimized and hand-tuned the math operations. That meant using the mobile processor’s SIMD instructions and tuning things like matrix multiplies to fit processing into all levels of cache memory.

In the end, we were able to get our networks to give us significantly better results while running about as fast as our old system—great for translating what you see around you on the fly. Sometimes new technology can seem very abstract, and it's not always obvious what the applications for things like convolutional neural nets could be. We think breaking down language barriers is one great use.

Posted by Otavio Good, Software Engineer, Google Translate

(Cross-posted on the Google Research Blog)

See the world in your language with Google Translate

Google Translate Official Blogger — Wed, 29 Jul 2015 15:48:00 +0000

The Google Translate app already lets you instantly visually translate printed text in seven languages. Just open the app, click on the camera, and point it at the text you need to translate—a street sign, ingredient list, instruction manual, dials on a washing machine. You'll see the text transform live on your screen into the other language. No Internet connection or cell phone data needed.

Today, we’re updating the Google Translate app again—expanding instant visual translation to 20 more languages (for a total of 27!), and making real-time voice translations a lot faster and smoother—so even more people can experience the world in their language.

Instantly translate printed text in 27 languages
We started out with seven languages—English, French, German, Italian, Portuguese, Russian and Spanish—and today we're adding 20 more. You can now translate to and from English and Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, Filipino, Finnish, Hungarian, Indonesian, Lithuanian, Norwegian, Polish, Romanian, Slovak, Swedish, Turkish and Ukrainian. You can also do one-way translations from English to Hindi and Thai. (Or, try snapping a pic of the text you’d like translated—we have a total of 37 languages in camera mode.)

To try out the new languages, go to the Google Translate app, set “English” along with the language you’d like to translate, and click the camera button; you'll be prompted to download a small (~2 MB) language pack for each.

Ready to see all of these languages in action?

And how exactly did we get so many new languages running on a device with no data connection? It’s all about convolutional neural networks (whew)—geek out on that over on our Research blog.

Have a natural, smoother conversation—even with a slower mobile network
In many emerging markets, slow mobile networks can make it challenging to access many online tools - so if you live in an area with unreliable mobile networks, our other update today is for you. In addition to instant visual translation, we’ve also improved our voice conversation mode (enabling real-time translation of conversations across 32 languages), so it’s even faster and more natural on slow networks.

These updates are coming to both Android and iOS, rolling out over the next few days.

Translate Community helps us get better every day
On top of today’s updates, we’re also continuously working to improve the quality of the translations themselves and to add new languages. A year ago this week, we launched Translate Community, a place for multilingual people from anywhere in the world to provide and correct translations. Thanks to the millions of language lovers who have already pitched in—more than 100 million words so far!—we've been updating our translations for over 90 language pairs, and plan to update many more as our community grows.

We’ve still got lots of work to do: more than half of the content on the Internet is in English, but only around 20% of the world’s population speaks English. Today’s updates knock down a few more language barriers, helping you communicate better and get the information you need.

Posted by Barak Turovsky, Product Lead, Google Translate

(Cross-posted on the Official Google Blog)

How Google Translate squeezes deep learning onto a phone

Research Blog — Wed, 29 Jul 2015 13:00:00 +0000

Posted by Otavio Good, Software Engineer, Google Translate

Today we announced that the Google Translate app now does real-time visual translation of 20 more languages. So the next time you’re in Prague and can’t read a menu, we’ve got your back. But how are we able to recognize these new languages?

In short: deep neural nets. When the Word Lens team joined Google, we were excited for the opportunity to work with some of the leading researchers in deep learning. Neural nets have gotten a lot of attention in the last few years because they’ve set all kinds of records in image recognition. Five years ago, if you gave a computer an image of a cat or a dog, it had trouble telling which was which. Thanks to convolutional neural networks, not only can computers tell the difference between cats and dogs, they can even recognize different breeds of dogs. Yes, they’re good for more than just trippy art—if you're translating a foreign menu or sign with the latest version of Google's Translate app, you're now using a deep neural net. And the amazing part is it can all work on your phone, without an Internet connection. Here’s how.

Step by step

First, when a camera image comes in, the Google Translate app has to find the letters in the picture. It needs to weed out background objects like trees or cars, and pick up on the words we want translated. It looks at blobs of pixels that have similar color to each other that are also near other similar blobs of pixels. Those are possibly letters, and if they’re near each other, that makes a continuous line we should read.

Some of the “dirty” letters we use for training. Dirt, highlights, and rotation, but not too much because we don’t want to confuse our neural net.

The third step is to take those recognized letters, and look them up in a dictionary to get translations. Since every previous step could have failed in some way, the dictionary lookup needs to be approximate. That way, if we read an ‘S’ as a ‘5’, we’ll still be able to find the word ‘5uper’.

Finally, we render the translation on top of the original words in the same style as the original. We can do this because we’ve already found and read the letters in the image, so we know exactly where they are. We can look at the colors surrounding the letters and use that to erase the original letters. And then we can draw the translation on top using the original foreground color.

Crunching it down for mobile

Now, if we could do this visual translation in our data centers, it wouldn’t be too hard. But a lot of our users, especially those getting online for the very first time, have slow or intermittent network connections and smartphones starved for computing power. These low-end phones can be about 50 times slower than a good laptop—and a good laptop is already much slower than the data centers that typically run our image recognition systems. So how do we get visual translation on these phones, with no connection to the cloud, translating in real-time as the camera moves around?

We needed to develop a very small neural net, and put severe limits on how much we tried to teach it—in essence, put an upper bound on the density of information it handles. The challenge here was in creating the most effective training data. Since we’re generating our own training data, we put a lot of effort into including just the right data and nothing more. For instance, we want to be able to recognize a letter with a small amount of rotation, but not too much. If we overdo the rotation, the neural network will use too much of its information density on unimportant things. So we put effort into making tools that would give us a fast iteration time and good visualizations. Inside of a few minutes, we can change the algorithms for generating training data, generate it, retrain, and visualize. From there we can look at what kind of letters are failing and why. At one point, we were warping our training data too much, and ‘$’ started to be recognized as ‘S’. We were able to quickly identify that and adjust the warping parameters to fix the problem. It was like trying to paint a picture of letters that you’d see in real life with all their imperfections painted just perfectly.

To achieve real-time, we also heavily optimized and hand-tuned the math operations. That meant using the mobile processor’s SIMD instructions and tuning things like matrix multiplies to fit processing into all levels of cache memory.

In the end, we were able to get our networks to give us significantly better results while running about as fast as our old system—great for translating what you see around you on the fly. Sometimes new technology can seem very abstract, and it's not always obvious what the applications for things like convolutional neural nets could be. We think breaking down language barriers is one great use.

Google Translate keeps getting better with your help

Google Translate Official Blogger — Mon, 29 Jun 2015 21:02:00 +0000

People use Google Translate a whole lot—we translate over 100 billion words a day! However, in the past, our translation systems have generally been better at making sense of government and business documents than in helping people casually communicate.

But that’s all changing thanks to people like you and a recent update we rolled out. So the next time you translate informal speech in Google Translate, you might just find a better translation. Here's an example of how it’s improved:

So how exactly are people like you impacting Google Translate? Well, with Translate Community hundreds of thousands of people have generously donated their time in service of cross-language communication. It’s fun and really easy: tell us what languages you speak; choose to either see a phrase and translate it on your own or correct current translations already in the system. Based on translations from the community, we will incorporate corrections and over time learn the language a little better.

There’s a whole lot more work to do, but with more help from everyday people through Translate Community, we can continue to improve the 90 languages we already speak and keep adding more.

Posted by Aaron Babst, Community Program Manager, Google Translate

Improving Google Translate during I/O

Google Translate Official Blogger — Thu, 18 Jun 2015 20:23:00 +0000

During the Translate Community: Google I/O Challenge nearly 2.5 million phrases or about 12 million words were translated and validated by participants during Google I/O and beyond. From Afrikaans to Zulu, we saw approximately 75,000 people representing all of the 117 languages available in Google Translate Community take the lead and improve Google Translate for the languages they speak.

Some of the top contributing languages were what you might expect based on the number of speakers of each language; Spanish, Russian, French and Portuguese led the way through the challenge and languages like Bengali and Vietnamese notably moved their way up the rankings.

Of the languages that are not yet in Google Translate, Kyrgyz speakers shined the brightest with nearly 40,000 phrases translated and validated during the challenge. The Kyrgyz community has continued to plan events and rally to help add their language to Google Translate.

Thank you to the I/O Extended event organizers, Google Developer Groups and everyone who contributed to improving their language in Google Translate throughout this 10-day-challenge. We're excited to continue to work together in improving Google Translate.

Aaron Babst, Google Translate, Community Program Manager

Translate Community: Google I/O Challenge

Google Translate Official Blogger — Tue, 26 May 2015 16:30:00 +0000

For the last 10 months, multilingual users around the world have flocked to the Google Translate Community to help improve their language(s) on Google Translate through translating and validating common phrases.

Since launch, we've seen some amazing contributions, from Kyrgyz speakers who are getting us closer to adding their language to Google Translate, to Bengali speakers who organized 80 translate-a-thon events, significantly increasing translation quality for their language.

Translate Community: Google I/O Challenge (May 26 - June 5, 2015)
Now, we're challenging all Google I/O attendees (onsite and offsite!) to represent your language(s) during the Translate Community: I/O Challenge running from May 26 to June 5, 2015. Our goal is to reach over 5 million total contributions during the challenge.

You can make meaningful contributions in just a few minutes, and remember that all contributions matter—we encourage you to spread the word in your local community and amongst your friends and family to increase the contributions for your language(s). More contributions mean higher quality translations for your language(s), or helping your language(s) become supported on Google Translate, if they aren’t yet.

To get started:

Sign up in the new version of Translate Community at g.co/translate/io
Set your language(s) and contribute with as many high-quality translations / validations you have time for
Invite others to join the challenge and show support for your language on social with the official #io15 & #loveyourlanguage hashtags

You can follow which languages are getting the most contributions on our Google+ page, where we’ll post updates on who's leading the way throughout the challenge. Besides helping your language rise to the top of our leaderboard, if you’re one of the top high-quality contributors, you’ll get a Google Translate certificate for your linguistic legerdemain and might even get a shoutout on our social channels.

Built with Polymer
In the spirit of Google I/O, we recently released a new version of the Translate Community using Polymer. In addition to supporting your language, be one of the first to try out the new look of Translate Community.

This new version takes advantage of Web Components in Polymer. We're one of the first teams at Google to use Polymer this way—it’s now much easier to add new features like badges, upgrade our design, and ensure it works great on smartphones and tablets, in addition to desktop. We're looking forward to leading the way by offering our community a fun and engaging place to make a positive impact.

Posted by Aaron Babst, Google Translate, Community Program Manager

A month of language love in Southeast Asia আপনার ভাষা প্রেম သင့်ဘာသာစကား ကိုချစ်မြတ်နိုး Yêu lắm Tiếng Việt ơi! รักภาษาของคุณ

Google Translate Official Blogger — Thu, 09 Apr 2015 03:22:00 +0000

Have you ever slashed the wind with your friends? Attached a gold leaf to the back of a Buddha statue? Or caught the moon in your hands?

You probably have, but if you don’t speak Vietnamese, Thai or Bengali you probably called it something else. These are some phrases Google Translate learned to understand a little better during the first of a series of translate-a-thons held over the last month in Bangladesh, Myanmar, Vietnam and Thailand, part of a “Love your Language” project to get languages better represented on the Web. (For those playing at home, the Vietnamese call it slashing the wind when they gossip, the Thais say they attach a gold leaf to the back of a Buddha statue when they do something selfless, and Bengalis say they’ve caught the moon in their hand when they receive something rare).

Google Translate provides free translation in 90 languages, but for those that don’t have much presence on the Web - like Myanmar, Bengali, Vietnamese and Thai - it could use a little help.

This is where the Translate Community tool and passionate language speakers can make a difference. By letting people validate, match, rate and supply translations, it can boost the translation of these languages online for millions of people.

Try it out yourself at translate.google.com/community

Since kicking off on International Mother Tongue Day (21 Feb), more than 50,000 people have come together, online and off, to use this tool to improve translations for Bengali, Myanmar, Vietnamese and Thai. They gathered at startup hubs in Yangon and university campuses in Vietnam, Bangladesh and Thailand.

This gentleman showed up at Phandeeyar Innovation Hub in Yangon with a handwritten list of phrases he wanted Google to get right.

So far, more than 100 translate-a-thons have been held and more than 10 million words have been added. That's 17 times more words than Tolstoy used for War and Peace, 12 times the number of words in the English version of the Bible.

It's made a huge difference. The quality of Bengali translations are now twice as good as they were before human review. While in Thailand, Google Translate learned more Thai in seven days with the help of volunteers than in all of 2014.

The following graph show the spike in Translate Community inputs over the last month, March 26 saw a major spike for Bangladesh Independence day, setting a new record for the largest volume of translations contributed in 24 hours.

Google Translate Community surfaces a random selection of popular words and phrases that users are asking Google Translate to explain in their language — from music lyrics, to local recipes, to human rights.

Teaching Google Vietnamese at the University of Technology in Ho Chi Minh City

Teaching Google Vietnamese at the University of Technology in Ho Chi Minh City We sometimes think the offline world and online world are separate. They're not. A huge thank you to all the people that joined us for the Love your Language series of events. Your efforts have made it easier for people from downtown Dhaka to upcountry Thailand to access the web in a language they understand.

Teaching Thai at Siam University International College

And the improvements don’t need to stop. By joining the Translate Community you can join us in making the web work better for everyone — no matter what language you speak.

Posted by Svetlana Kelman, Program Manager, Google Translate
(Cross-posted from the Asia Pacific Blog)

Celebrate Mother Language Day by joining the Google Translate Community

Aaron Babst — Sat, 21 Feb 2015 00:01:00 +0000

February 21 marks the 15th anniversary of the UNESCO declaration of International Mother Language Day. Since then each Mother Language Day has promoted the preservation and protection of the approximately 7,000 languages that are spoken throughout the world, half of which are estimated to become extinct in a few generations.

In honor of Mother Language Day 2015, we've decorated the Google Translate homepage with an illustration that celebrates this year's theme of "inclusive education through and with language." Language education helps people connect with others both within and outside their local community.

Click on our illustration on the homepage to visit the Google Translate Community where you can help add new languages to Google Translate and improve those that are currently supported. We've already seen Cantonese, Kyrgyz and Pashto speakers contribute a lot, and we hope to continue our collaboration with these communities so we can eventually add these languages.

We hope you join us for Mother Language Day to improve translation for everyone and show pride for your language. We'll be highlighting the top languages with the most contributions to Translate Community over the next 48 hours on our Google+ page. Show some love for your language and help it get to the top of the list by contributing today!

Posted by Aaron Babst, Community/Program Manager, Google Translate

(Cross-posted on the Inside Search Blog)

Hallo, hola, olá to the new, more powerful Google Translate app

Google Translate Official Blogger — Wed, 14 Jan 2015 08:01:00 +0000

Often the hardest part of traveling is navigating the local language. If you've ever asked for "pain" in Paris and gotten funny looks, confused "embarazada" with "embarrassed" in Mexico, or stumbled over pronunciation pretty much anywhere, you know the feeling. Now Google Translate can be your guide in new ways. We’ve updated the Translate app on Android and iOS to transform your mobile device into an even more powerful translation tool.

Instant translation with Word Lens
The Translate app already lets you use camera mode to snap a photo of text and get a translation for it in 36 languages. Now, we’re taking it to the next level and letting you instantly translate text using your camera—so it’s way easier to navigate street signs in the Italian countryside or decide what to order off a Barcelona menu. While using the Translate app, just point your camera at a sign or text and you’ll see the translated text overlaid on your screen—even if you don't have an Internet or data connection.

This instant translation currently works for translation from English to and from French, German, Italian, Portuguese, Russian and Spanish, and we’re working to expand to more languages.

Have an easier conversation using the Translate app

When talking with someone in an unfamiliar language, conversations can... get... realllllllly... sloowwww. While we’ve had real-time conversation mode on Android since 2013, our new update makes the conversation flow faster and more naturally.

Starting today, simply tap the mic to start speaking in a selected language, then tap the mic again, and the Google Translate app will automatically recognize which of the two languages are being spoken, letting you have a more fluid conversation. For the rest of the conversation, you won’t need to tap the mic again—it'll be ready as you need it. Asking for directions to the Rive Gauche, ordering bacalhau in Lisbon, or chatting with your grandmother in her native Spanish just got a lot faster.

These updates will be coming to both Android and iOS, rolling out over the next few days. This is the first time some of these advanced features, like camera translations and conversation mode, will be available for iOS users.

More than 500 million people use Google Translate every month, making more than 1 billion translations a day to more easily communicate and access information across languages. Today’s updates take us one step closer to turning your phone into a universal translator and to a world where language is no longer a barrier to discovering information or connecting with each other.

Posted by Barak Turovsky, Product Lead, Google Translate

Google Translate – 10 More Languages with your Help

Google Translate Official Blogger — Thu, 11 Dec 2014 22:14:00 +0000

Cross-posted on the Inside Search Blog

Whether you're teaching yourself a new language or trying to make a new friend, Google Translate can be a powerful tool for crossing language barriers. Today, we're adding 10 languages to Translate, bringing our total number of supported languages to 90. These 10 new languages will allow more than 200 million additional people to translate text to and from their native languages. These languages are available now on translate.google.com and will roll out soon to our mobile apps and to the built-in translation functionality in Chrome.

If it weren't for the active Translate Community participation, we wouldn't be able to launch some of these languages today. While our translation system learns from translated data found on the web, sometimes we need support from humans to improve our algorithms. We're very grateful for all the support we're getting today and we hope that together with our community, we can continue improving translation quality for the languages we support today and add even more languages in the future.

Spotlight on our new languages

Africa gets more language coverage with Chichewa, Malagasy, and Sesotho:

Chichewa (Chinyanja) is spoken by 12 million people in Malawi and surrounding countries. It is one of 55 languages used in the greetings that now travel the galaxy on the Voyager interstellar probes.
Malagasy is spoken by 18 million people in Madagascar, where it is the national language. It is one of only a few languages which puts the verb first in sentences, followed by the object and then the subject.
Sesotho has 6 million native speakers. It is the national language of Lesotho and one of 11 official languages in South Africa.

In India and Southeast Asia, we are adding Malayalam, Myanmar, Sinhala, and Sundanese:

Malayalam (മലയാളം), with 38 million native speakers, is a major language in India and one of that country’s 6 classical languages. It’s been one of the most-requested languages, so we are especially excited to add Malayalam support!
Myanmar (Burmese, မြန်မာစာ) is the official language of Myanmar with 33 million native speakers. Myanmar language has been in the works for a long time as it's a challenging language for automatic translation, both from language structure and font encoding perspectives. While our system understands different Myanmar inputs, we encourage the use of open standards and therefore only output Myanmar translations in Unicode.
Sinhala (සිංහල) is one of the official languages of Sri Lanka and natively spoken by 16 million people. In September the local community in Sri Lanka organized Sinhala Translate Week, and since then, participants have contributed tens of thousands of translations to our system. We're happy to be able to release Sinhala as one of the new languages today!
Sundanese (Basa Sunda) is spoken on the island of Java in Indonesia by 39 million people. While Sundanese does have its own script, it is today commonly written using the Latin alphabet, which is what our system uses.

In Central Asia, we are adding Kazakh, Tajik, and Uzbek:

Kazakh (Қазақ тілі) with 11 million native speakers in Kazakhstan. We've received strong support from Kazakh language enthusiasts, and we hope to continue collaborating with the local communities in the region to add even more languages in the future, including Kyrgyz.

Tajik (Тоҷикӣ), a close relative to modern Persian, is spoken by more than 4 million people in Tajikistan and beyond.
Uzbek (Oʻzbek tili) is spoken by 25 million people in Uzbekistan. In addition to receiving Uzbek community support, we've incorporated the Uzbek dictionary by Shavkat Butaev into our system.

We’re just getting started with these new languages and have a long way to go. You can help us by suggesting your corrections using "Improve this translation" functionality on Translate and contributing to Translate Community.

Posted by the Google Translate engineering team

Translate web pages more easily with the new Translate Chrome Extension

Google Translate Official Blogger — Wed, 15 Oct 2014 22:23:00 +0000

When you're browsing the web, you might come across a page where some of the text is in a different language. With the new update to the Google Translate Chrome extension, you can translate just that piece of text, without worrying about the rest of the page.

Simply highlight the text that you want to translate, and then click the Translate icon that appears. You can also right click and choose "Google Translate". If you click the Translate icon in the upper right of your browser window, with no text highlighted, you can translate the entire web page.

You can download and try the Translate extension from the Chrome Web Store; if you already have the extension installed, it will be updated automatically.

The Translate team is working hard to connect people by breaking language barriers across computers, mobile devices and Internet browsers. Our users make more than 1 billion translations a day, and we hope that our recent update will make their translation tasks a little easier!

Posted by Chao Tian, Software Engineer, Google Translate

Translate Community: Help us improve Google Translate!

Google Translate Official Blogger — Fri, 25 Jul 2014 17:56:00 +0000

Google Translate helps billions of people communicate and learn new languages, but it could always use a little help. Luckily, there are a lot of multi-lingual people around the world who have offered to pitch in. We’ve just launched a new Translate Community where language enthusiasts can help us improve translation quality for the 80 languages we support, as well as help us in launching new languages.

In the new community, you'll find options to help with a variety of things, including generating new translations and rating existing ones. Over time, you’ll find more ways to contribute, as well as get more visibility into the impact of your contributions and the activity across the community. We will also localize Community pages to support your preferred display language. If you have feedback and ideas about improving and growing our community, we'd love to hear it so please don't hesitate to submit it via "Send feedback" link on the bottom of the page.

Even if you don’t have time to dedicate towards Translate Community, we want to make it easier for you to make translation corrections when you find a problem. We’ve recently made it possible for you to suggest an entirely new translation directly in Google Translate.

When you spot a translation that you’d like to edit, click the "Improve this translation" pencil icon and click "Contribute" to submit your suggestion to us. We plan to incorporate your corrections and over time learn your language a little better.

So help us fine-tune and launch languages you care about: join our community efforts and make translations more accurate when you use Google Translate!

Posted by Sveta Kelman, Program Manager, Google Translate

Google Translate – now in 80 languages

Unknown — Tue, 10 Dec 2013 18:29:00 +0000

Whether you’re trekking to a new place or simply trying to communicate with someone who doesn’t share a language with you, Google Translate can help you connect to new information and people. Today, we’re launching 9 new languages that span Africa, Asia, and Oceania and have over 200 million native speakers, collectively.

Spotlight on our new languages

In Africa, we’re adding Somali, Zulu, and the 3 major languages of Nigeria.

Hausa (Harshen Hausa), spoken in Nigeria and neighboring countries with 35 million native speakers
Igbo (Asụsụ Igbo) spoken in Nigeria with 25 million native speakers
Yoruba (èdè Yorùbá) spoken in Nigeria and neighboring countries with 28 million native speakers

Somali (Af-Soomaali) spoken in Somalia and other countries around the Horn of Africa with 17 million native speakers
Zulu (isiZulu) spoken in South Africa and other south-western African countries with 10 million native speakers

Throughout Asia, we’re launching languages spoken in Mongolia and South Asia.

Mongolian (Монгол хэл), official language in Mongolia and also spoken in parts of China with 6 million native speakers
Nepali (नेपाली), spoken in Nepal and India with 17 million native speakers
Punjabi language (ਪੰਜਾਬੀ) (Gurmukhi script), spoken in India and Pakistan with 100 million native speakers

Thanks to the volunteer effort of passionate native speakers in New Zealand, we’re adding the language of the Maori people.

Maori (Te Reo Māori), spoken in New Zealand with 160 thousand speakers

Punjabi on the Google Translate desktop web app

Mongolian on the Google Translate Android app

-----

You can help to add your language to Google Translate

Although Google Translate is an automatic tool, a new language sometimes needs a little love from native speakers to get off the ground. You can help launch your language by volunteering to help us gather and translate texts in your language. Sign up with this form. We’re also constantly fine-tuning our translations. You can help with these efforts by clicking the translated text and editing it to be correct.

As always, we realize that we’re just getting started and have a long way to go. But hopefully these new languages in Translate help you to connect with new friends and new cultures.

Posted by Arne Mauser, Software Engineer

Have an easier conversation with Google Translate on Android

Unknown — Wed, 20 Nov 2013 21:47:00 +0000

Cross-posted from the Inside Search Blog

Have you ever been in that frustrating situation where you meet someone -- yet can’t communicate because you don’t speak each other’s language? Well, hopefully communication can become a whole lot easier with the launch of the new Google Translate app for Android. The app now features faster and simpler speech translation, additional language support, and a sleek new look.

Converse without boundaries

Let’s say you're taking your first vacation abroad and decide to head to Spain. The only problem? You don't speak Spanish. Now -- equipped with just your Android device -- you can have a fully translated back-and-forth conversation from Spanish to English with very little work. All you need to do is open up your Translate app and press the microphone icon. We’ve also added gesture support, so with a simple turn of the screen, you can switch back and forth between languages. This makes ordering food in that authentic Tapas restaurant a whole lot easier!

More translate options for more languages

With today’s updated Translate app, we also offer more language support for our handwriting feature, allowing you to directly write words in Hebrew, Greek, Javanese, and Esperanto on your device screen and have them translated on the fly. You can also use our camera translation feature to take a photo of written text with your Android device and highlight which words you’d like to be translated, now including additional language support for Malay and Ukranian.

We hope Google Translate can continue to help break down more language barriers in easier ways, all on your mobile device. We'll be rolling the update out via the Google Play Store today and tomorrow. We hope you give it a whirl!

Posted by Matthew Gaba, Product Manager

A fresh look for Google Translate on iOS, with more languages and new features

Unknown — Thu, 19 Sep 2013 21:55:00 +0000

Cross posted from the Inside Search Blog.

When you’re trekking around a new place or trying to communicate with someone who speaks a different language, Google Translate helps break down the language barrier. Today we updated and optimized the Google Translate app for iOS 7, where you’ll see a fresh new look, handwriting support, and 70+ languages.

If you’re on vacation in Kyoto, and want to learn more about an exotic flower arrangement, use text-input to type in your question and translate from English to Japanese with ease. You can also hear your translation spoken back to you in Japanese.

If a shopkeeper in Paris wants to talk with a visitor from Spain, they can tap the microphone, speak naturally, and quickly translate from French to Spanish with a few simple taps.

If you are an expat living in China and want to know what’s on the menu, use the Handwrite feature to discover a tasty new treat. Tap the Handwrite icon, and input natural handwriting in nearly 50 languages.

Google Translate is useful in many situations, especially while you’re on the go. We hope you enjoy the new design and features.

Posted by Masakazu Seno, Software Engineer, Google Translate

Translate Google+ posts and comments with Google Translate

Unknown — Tue, 20 Aug 2013 15:56:00 +0000

Whenever there's a Google+ public post or comment that isn’t in your language, you'll now see a "Translate" link underneath the text. Clicking the link translates the text in-line, and clicking again returns to the original. (You can set/check your language prefences here: www.google.com/settings/account )

The Google Translate team is always working to make information more accessible to individuals around the world. In Google+ this means bringing people together regardless of their written language, and breaking down language barriers that can limit the exchange of ideas.

We’re rolling out the feature gradually on desktop, so look for the new “Translate” link, and let us know your thoughts!

Posted by +Ed Chi, Research Scientist, and +Lichan Hong, Software Engineer

Sometimes It’s Easiest to Just Write It Down

Josh E — Wed, 24 Jul 2013 19:36:00 +0000

Last year we brought handwriting input to Google Translate for Android. Earlier this year, we updated Google Input Tools on desktop by adding new virtual keyboards, input method editors, and transliteration input tools. Today, we take our input tools one step further, by bringing handwriting input to the Google Translate homepage.

Handwriting input lets you translate a written expression, even if you don’t know how to type the characters. For example, suppose you see the Chinese expression “饺子” and want to know its meaning in English, but have no idea how to type these characters. Using the new handwriting input tool, you can simply draw these characters on your screen and instantly see the translation.

Once you have chosen your input language, you will see the input tools icon at the bottom of the text area. Click the input tools icon to switch to handwriting in the drop-down menu. You can then begin drawing your text on the main panel of the handwriting tool. You can draw multiple characters at once.

We currently have handwriting support for 45 languages, including Chinese, Japanese and Korean. Handwriting input is also available in the Google Input Tools Chrome extension. Other text input tools in Translate include virtual keyboards, input method editors, and transliteration. They are also available in other Google products, including Gmail, Drive, Chrome, and Android. We hope handwriting will make your translation experience easier than ever!

Posted by Xiangye Xiao, Product Manager

Take your Phrasebook on the go—and translate by camera in 16 more languages

Unknown — Wed, 08 May 2013 22:37:00 +0000

When you’re traveling in another country, you want quick access to your favorite translated phrases—whether it’s “Where can I find a museum?” or “Do you know where the bathroom is?” Google Translate lets you save these translations in your Phrasebook, but you still could not easily access them on the go from your phone or tablet. Starting today, you can automatically sync the phrases in your Phrasebook to your Android device using the Google Translate mobile app, so you can carry your most useful phrases with you wherever you go.

To get started, select Phrasebook in the app menu of the Google Translate app for Android. (Notice that Phrasebook replaces the Favorites feature; your saved phrases are now part of your Phrasebook.) To sync your phrases, simply sign in to your Google Account by tapping the ‘Sign in’ button at the top of your Phrasebook.

With your favorite phrases synced across devices, we hope you’ll never be at a loss for words again.

Last but not least, this latest release of Google Translate for Android sees a significant improvement to the camera-input feature. You can now use camera-input to find translations in 16 additional languages: Bulgarian, Catalan, Danish, Estonian, Finnish, Croatian, Hungarian, Indonesian, Icelandic, Lithuanian, Latvian, Norwegian, Romanian, Slovak, Slovenian, and Swedish.

Happy translating!

Minqi Jiang, Associate Product Manager, on behalf of the Google Translate Team

More than 70 of the world’s languages in the blink of an eye

Unknown — Wed, 08 May 2013 12:00:00 +0000

If you took a quick snapshot of content available on the web, you might think that everyone around the world spoke English, Chinese, French or Spanish. But in fact, millions of people around the world speak an incredible array of languages that currently have a small presence across the web.

Google Translate helps bridge the divide between the content available online and people’s ability to access that information. Starting today, you can translate another five languages using Google, which combined are spoken by more than 183 million people around the globe:

Bosnian is an official language in Bosnia and Herzegovina that’s also spoken in regions of neighboring countries and by diaspora communities around the world.
Cebuano is one of the languages spoken in the Philippines, predominantly in the middle (Visayas) and southern (Mindanao) regions of the nation.
You can hear the Hmong language spoken in many countries across the world, including China, Vietnam, Laos, Thailand and throughout the United States.
Javanese is the second most-spoken language in Indonesia (behind Indonesian), with 83 million native speakers.
Marathi is spoken in India and has 73 million native speakers. Google Translate already supports several other Indian languages: Bengali, Gujarati, Hindi, Kannada, Tamil, Telugu and Urdu.

With the exception of Bosnian, these new languages are “alpha,” meaning while the quality isn’t perfect, we will continue to test and improve them over time.

You can access Translate on the web at https://translate.google.com, on your Android or iOS device, or via Chrome and in Gmail. We are excited to reach the 70+ language milestone, and we look forward to continuing to add more languages.

Bosnian: Google Prevodilac sada podržava više od 70 jezika!

Cebuano: Google sa Translate misuporta na karon sa kapin sa 70 ka mga!

Hmong: Google Translate nim no txhawb nqa tshaj li 70 hom lus!

Javanese: Google Translate saiki ndhukung luwih saka 70 basa!

Marathi: Google भाषांतर आता 70 पेक्षा जास्त भाषांचे समर्थन करते!

Posted by Sveta Kelman, Program Manager, Google Translate

Google Translate now supports Khmer

Unknown — Fri, 19 Apr 2013 01:20:00 +0000

What better way to start Cambodian new year than with the addition of the Khmer language to Google Translate as our 66th supported language. We hope that this will help open up the web to Khmer speakers and likewise make Khmer content more accessible to the rest of the world.

Our focus is and always will be our users. The Google Translate team works hard to improve the quality of our translations so that each newly launched language is of a quality good enough to help the users who rely on it. Khmer now meets our standards to be launched with “alpha” status. That means it is an early version of the translation system that will be usable in many situations, but may not be adequate for all.

Today’s Khmer launch comes with these useful features: virtual keyboard (in case you want to type in Khmer but do not have Khmer keyboard handy) and ability to read Khmer text phonetically for users who don't read Khmer alphabet.

Khmer is a challenging language for translation systems for two reasons: There isn’t a lot of Khmer data on the web and words are not usually separated by spaces; so in addition to teaching our translation system a new language, it also has to learn how to separate words (what we call segmentation).

Over time, we will improve the system and make our Khmer translations better. We constantly improve our algorithm when we find new translations and learn from your alternative translations.

If your language is not yet supported, please rest assured that our team is working hard behind the scenes to support additional languages. The more your language is used on publicly available websites with translations into other languages, the sooner we are likely to start supporting it. So please use your language on the web and help us collect new translations by uploading your translations with the Translator Toolkit.

សួស្ដីឆ្នាំថ្មី (Happy New Year)!

Post by Arne Mauser, Software Engineer, on behalf of the Google Translate Team

The World’s Languages in Your Pocket (No Internet Required)

Unknown — Wed, 27 Mar 2013 18:18:00 +0000

Have you ever found yourself in a foreign country, wishing you knew how to say "I'm lost!" or "I'm allergic to peanuts”? The Internet and services like Google Translate can help—but what if you don't have a connection?

Today we're launching offline language packages for Google Translate on Android (2.3 and above) with support for fifty languages, from French and Spanish to Chinese and Arabic.

You can select [Offline Languages] in the app menu to see all the offline language packages available for download. To enable offline translation between any two languages, you just need to select them in the offline languages menu. Once the packages are downloaded, you're good to go.

While the offline models are less comprehensive than their online equivalents, they are perfect for translating in a pinch when you are traveling abroad with poor reception or without mobile data access.

So go out and explore another language or another culture without worrying about Internet access. There’s a whole world offline out there.

Posted by Minqi Jiang, Associate Product Manager, on behalf of the Google Translate Team

Never Forget a Useful Phrase Again – Introducing Phrasebook for Google Translate

Unknown — Thu, 14 Mar 2013 21:19:00 +0000

Your knowledge of a language is largely determined by how well you can say the right things at the right time. But with so many useful phrases out there, it can be hard to keep track of them all, let alone recall them when needed.

With Google Translate, you can find the right thing to say, but you may not remember the translation at the right time. You might find yourself performing the same translation again and again, until you finally commit the translation to memory.

Phrasebook for Google Translate jumpstarts this slow learning process by allowing you to save the most useful phrases to you, for easy reference later on, exactly when you need them. By revisiting the useful phrases in your Phrasebook from time to time, you can turn any brief translation into lasting knowledge.

It’s easy to start using Phrasebook. Simply click the star under the translated text to save the translation in your Phrasebook.

To view your Phrasebook, simply click the Phrasebook icon above the upper-right corner of the box containing the translation.

Click any phrase in your Phrasebook to load it back in the translation area. Using the Phrasebook controls, you can filter your phrases by language pair or search for a specific phrase. You can also easily listen to each phrase by hovering over the entry and selecting the text-to-speech icons.

We hope your new Phrasebook will come in handy as you use Google Translate. We'd love to hear any feedback you have about this new feature. You can tell us what you think about Phrasebook through the "Send Feedback" option at the bottom of the Google Translate homepage.

- The Google Translate Team

Get your YouTube video captions professionally translated into 36 languages

Jeff — Wed, 20 Feb 2013 19:03:00 +0000

(Cross-posted from the Official YouTube Partners & Creators Blog)

Back in September, we launched a feature that made it easier to make your YouTube video accessible in more than 300 languages and help grow your audience globally, by translating the video’s captions yourself or inviting friends or people you know to help translate. Now you can connect directly with translation vendors and pay to get your captions translated quickly and professionally.

When you request a translation for your captions in YouTube, we’ll display a list of vendors along with their estimated pricing and delivery date so you can easily compare. We’ve initially collaborated with two companies, Gengo and Translated.net, to make their services available to you and to streamline the ordering process.

Just click “Start order” next to the vendor you’d like to use. This will then create an order and direct you to the vendor’s website to complete payment. When the translator completes the translation, they’ll send the translated caption directly back to YouTube. Once you approve, the translated caption will now be available for all your viewers!

Need to add a caption track to your video?

Before you can translate your video, you’ll first need a caption track for your video. One of the easiest and quickest way to create a caption track is to create or upload a transcript of your video. YouTube will then automatically sync your transcript with the video and create the time codes to generate the caption track. For more info, watch this video or take a look at this helpful guide.

Don’t know which languages to translate your video into?

If your video has already been published, let YouTube Analytics help. YouTube Analytics can show you the top geographies viewing your video, so you can choose the languages spoken in these countries. Learn more about YouTube Analytics here.

Posted by Jeff Chin, Product Manager, who recently watched the “H+” digital series which has been captioned and subtitled into Spanish.

Introducing Our New Input Tools

Unknown — Wed, 06 Feb 2013 20:24:00 +0000

Considering the vast number of ways that users type in our 65 supported languages, we are pleased to announce the integration of Google’s new input tools in Google Translate. We have always allowed you to choose among alternative input methods, but your choice was limited. For example, only one of four popular input methods for Chinese was previously available. Our new input tools greatly expand the set of available input methods for many languages.

A Cyrllic letter-printing telegraph keyboard

We believe that your choice of input tools is important, because the best way to input text with a keyboard varies from language to language, and even from person to person. Every language has its own set of popular input methods, each familiar to its own subset of users. For example, the Portuguese keyboard has two common layouts, one popular in Brazil and another in Portugal. In addition, given the popularity of Latin-alphabet keyboards, a transliteration input tool is often the preferred input method for many languages, allowing users to convert Latin-alphabet input into the proper written script. (Chinese has over 80,000 characters. Try fitting them all on a keyboard.) With the right transliteration input tools turned on, you can simply type “privet” to input привет, “tieng chao” for tiếng chào, and “nihao” for 你好.

It’s easy to start using our new input tools. Once you have chosen your input language, you will see the input tools icon at the bottom of the text area. Click the icon to turn on the input tool or switch to another input tool in the drop-down menu.

The new input tools are now also available in other Google products, including Gmail, Drive, Chrome, and Android, as well as in Windows. We hope our new input tools will make your translation experience easier than ever!

- The Google Translate Team

A Smarter Dictionary for Translation

Minqi Jiang — Wed, 31 Oct 2012 17:13:00 +0000

Mahatma Gandhi tells us that "Love is the strongest force the world possesses." Love comes in many forms, and each has different translations. Today, we are introducing three new features to Google Translate that help to distinguish among translations of a word, because no love should ever be lost in translation.

Reverse translations. Our users often tell us that they check our translations by translating them back into their original language. Reverse translations can distinguish translations of different meanings and reveal subtle differences among similar words. Each translation is now annotated with its most frequent reverse translations.

With reverse translations as a guide, you can pick from dozens of languages to tell your love that they are your darling (querido) and not just your hobby (afición).

Frequencies. The French novelist Gustave Flaubert was known to spend hours on end in pursuit of le mot juste—the perfect word. At Google, we prefer to deliver results in an instant, ranked in order of relevance. Frequency indicators now mark each translation as common, uncommon, or rare, based on the vast number of translations we use to train our system. The rarest translations are hidden by default, but appear easily with a click. Your search for the perfect translation should now be more efficient than ever.

Synonyms. Languages often contain different words that share a common meaning. Instead of one long list, our results now group synonymous translations together, so that you can quickly identify clusters of related words.

This feature is currently available only when translating into English, but we intend to support more languages soon.

We hope that these new features will help you explore the grand variety of words in the world's many languages. Consider this new, smarter dictionary for translation as one more way of saying “love” from all of us on the Google Translate team to you.

Posted by John DeNero, Research Scientist and Minqi Jiang, Associate Product Manager, Google Translate.

Build a global audience on YouTube by translating your captions

Jeff — Wed, 26 Sep 2012 18:38:00 +0000

(Cross-posted from the Official YouTube Partners & Creators Blog)

Growing a global audience on YouTube means having your videos reach many people, speaking many languages. So today we’ve made it easier for you to translate YouTube video captions into more than 300 languages. See more details in the help center, or follow the step-by-step instructions below:

Getting started
You’ll first need a caption track for your video, so if you don’t yet have one you can learn how to make one here. Select “Request translation” in the YouTube Video Manager, choose the languages you’d like to translate into, and click “Next.” We’ll create caption translation documents that you can now invite anyone to help translate, or you can translate yourself. To translate the captions yourself, select the language, and it’ll open up the caption translation document in the Google Translator Toolkit editor to help your translate faster.

Watch while you translate
To give you context on the captions, we’ve also embedded the YouTube video in the editor so you can watch as you translate. For several languages we’ll provide first draft of the translation using Google’s machine translation technology. We’ll also provide preview of what the translated caption looks like on the video so you can make sure the translated captions fit.

Publish and enjoy
Click “Publish to YouTube” when you’re finished, and we’ll publish the translated caption back to your YouTube video. If you’re not the video owner, we’ll notify the owner via email that there’s a pending translation waiting to be approved and published.

By providing translated captions, you’ll not only make your video globally accessible but also improve discoverability in other languages. Now you can increase your audience by reaching more people around the world.

Posted by Jeff Chin and Brad Ellis, product managers, who recently watched “Life in a Day” which is subtitled in 26 languages.

Translating Lao

Minqi Jiang — Thu, 13 Sep 2012 20:03:00 +0000

Today, we are adding Lao to Google Translate, making it our 65th supported language. We are excited to bring Lao content to users around the world, and to help Lao speakers access more of the world's web content in other languages.

The Google Translate team is constantly working to improve automatic translations, both for languages that have been available for some time, and for currently unavailable languages whose translation quality have yet to meet our launch standards. This work includes collecting new data from which our system can learn and grow smarter; changing the algorithms behind Google Translate; and improving the grammaticality of translations. There are many languages we work on that are not there yet but that we hope to launch in the future.

Support for Lao meets our launch standards, but translation quality is at the lower end compared to that of other languages we offer. We therefore designate Lao with an “alpha” status until we can make further improvements. While our Lao translations will be usable in some situations, like providing an English reader with the gist of an article written in Lao, they will fail in other situations where more precise translations are needed. We need your feedback in order to improve the quality of Lao translations.

There are two ways in which you can directly help us improve the quality of Lao translation, or that of any other language:

Provide alternate translations by clicking on words or phrases of the translated sentence like in the example below:

Use the Google Translator Toolkit to upload translations.

Your feedback is always greatly appreciated.

ຂອບໃຈຫຼາຍໆເດີ້(Thank you very much).

Posted by Thorsten Brants - Research Scientist, Google Translate

Point, tap, brush and listen

Edeguine — Thu, 09 Aug 2012 18:24:00 +0000

With our latest update to our Google Translate app for Android, we’re aiming to get one step closer to the Babel fish. By integrating Google Goggles’ optical character recognition (OCR) technology, we’ve made it possible for you to use the camera of your Android smartphone to input text without typing. This makes Google Translate for Android one of our most intelligent and machine learning-intensive apps. Speech recognition, handwriting recognition, OCR, and machine translation all rely on powerful statistical models built on billions of samples of data. Here’s how it comes together:

To use our new camera feature, push the camera button, point at some text, tap to freeze the picture, brush the part you want with your finger, et voila -- enjoy your machine translation. As usual, you can click the text-to-speech icons to listen to the source text or the translated text. We currently support optical character recognition for Czech, Dutch, English, French, German, Italian, Polish, Portuguese, Russian, Spanish, and Turkish, and we’re also working hard to get more languages on the list.

Now give it a try -- translate your favorite tapas menu items quicker when you’re visiting Barcelona, decipher those mysterious Australian roadsigns, and finally learn how to pronounce the name of your favorite Russian movie. Leave us a comment on Google Play to tell us what you think.

Posted by Etienne Deguine - Associate Product Manager for Google Translate

Observing words in their natural habitat – example sentences in Google Translate

Edeguine — Fri, 13 Jul 2012 17:21:00 +0000

Did you know that more than 5000 new words are created each year? At Google we’re always curious about new words from around the world, from all languages, and we think one of the best ways to understand and make sense of new words is by observing them in their natural habitat. Our latest feature does just that by providing you with example sentences taken from fresh new stories around the web.

To try out the feature, simply type a few words in the left-hand text box of Google Translate, and then click on the example sentence icon:

Along with alternate translations (a feature that lets you click on a word to see different translations), and our dictionary results (literal translations extracted from our dictionaries), we hope that being able to look at example sentences will make machine translation more useful for you -- and a little more educational. Stay tuned as we continue to improve and enrich our corpus of example sentences.

Posted by Etienne Deguine, Associate Product Manager, Google Translate

Now you can polish up Google’s translation of your website

Jeff — Wed, 30 May 2012 23:32:00 +0000

Since we first launched the Website Translator plugin back in September 2009, more than a million websites have added the plugin. While we’ve kept improving our machine translation system since then, we may not reach perfection until someone invents full-blown Artificial Intelligence. In other words, you’ll still sometimes run into translations we didn’t get quite right.

So today, we’re launching a new experimental feature (in beta) that lets you customize and improve the way the Website Translator translates your site. Once you add the customization meta tag to a webpage, visitors will see your customized translations whenever they translate the page, even when they use the translation feature in Chrome and Google Toolbar. They’ll also now be able to 'suggest a better translation' when they notice a translation that’s not quite right, and later you can accept and use that suggestion on your site.

To get started:

Add the Website Translator plugin and customization meta tag to your website
Then translate a page into one of 60+ languages using the Website Translator

To tweak a translation:

Hover over a translated sentence to display the original text
Click on 'Contribute a better translation'
And finally, click on a phrase to choose an automatic alternative translation -- or just double-click to edit the translation directly.

For example, if you’re translating your site into Spanish, and you want to translate Cat not to gato but to Cat, you can tweak it as follows:

If you’re signed in, the corrections made on your site will go live right away -- the next time a visitor translates a page on your website, they’ll see your correction. If one of your visitors contributes a better translation, the suggestion will wait until you approve it. You can also invite other editors to make corrections and add translation glossary entries. You can learn more about these new features in the Help Center.

This new experimental feature is currently free of charge. We hope this feature, along with Translator Toolkit and the Translate API, can provide a low cost way to expand your reach globally and help to break down language barriers.

Posted by Jeff Chin, Product Manager, Google Translate

Say hello (or olá or halo or salam) to automatic message translation in Gmail

Jeff — Tue, 01 May 2012 17:22:00 +0000

(Cross-posted from the Official Gmail Blog)

We're excited to announce three Gmail Labs graduations today: Automatic Message Translation, Smart Mute and Title Tweaks.

Automatic Message Translation
Did you ever dream about a future where your communications device could transcend language with ease? Well, that day is a lot closer. Back when we launched automatic message translation in Gmail Labs, we were curious to see how people would use it.

We heard immediately from Google Apps for Business users that this was a killer feature for working with local teams across the world. Some people just wanted to easily read newsletters from abroad. Another person wrote in telling us how he set up his mom’s Gmail to translate everything into her native language, thus saving countless explanatory phone calls (he thanked us profusely). I continue to use it to participate in discussions with the global Google offices I often visit.

Since message translation was one of the most popular labs, we decided it was time to graduate from Gmail Labs and move into the real world. Over the next few days, everyone who uses Gmail will be getting the convenience of translation added to their email. The next time you receive a message in a language other than your own, just click on Translate message in the header at the top of the message,

and it will be instantly translated into your language:

If you're bi-lingual and don't need translation for that language, just click on Turn off for: [language]. Or if you'd like to automatically have messages in that language translated into your language, click Always Translate. If you accidentally turned off the message translation feature for a particular language, or don't see the Translate message header on a message, click on the down arrow next to Reply at the top-right of the message pane and select the Translate message option in the drop-down.

Title Tweaks
With the graduation of Title Tweaks, we've changed the text in the browser tab so that you can more easily see if you have new messages. The tab now reads "Inbox (20) - user@example.com - Gmail" instead of "Gmail - Inbox (20) - user@example.com.”

Smart MuteWe've made improvements to muting based on the graduation of the Smart Mute lab so you can be sure that noisy email threads stay out of your inbox. You can learn more about muting email threads in the help center.

In addition to graduating these three labs, we'll also be retiring some less popular labs over the next few days: Old Snakey, Mail Goggles, Mouse Gestures, Hide Unread Counts, Move Icon Column, Inbox Preview, Custom Date Formats and SMS in Chat gadget. Please note that the SMS in Chat lab is not being retired, just the gadget associated with it.

Posted by Jeff Chin, Product Manager, Google Translate

Breaking down the language barrier—six years in

Edeguine — Thu, 26 Apr 2012 18:01:00 +0000

Cross-posted from the Official Google Blog.

The rise of the web has brought the world’s collective knowledge to the fingertips of more than two billion people. With just a short query you can access a webpage on a server thousands of miles away in a different country, or read a note from someone halfway around the world. But what happens if it’s in Hindi or Afrikaans or Icelandic, and you speak only English—or vice versa?

In 2001, Google started providing a service that could translate eight languages to and from English. It used what was then state-of-the-art commercial machine translation (MT), but the translation quality wasn’t very good, and it didn’t improve much in those first few years. In 2003, a few Google engineers decided to ramp up the translation quality and tackle more languages. That's when I got involved. I was working as a researcher on DARPA projects looking at a new approach to machine translation—learning from data—which held the promise of much better translation quality. I got a phone call from those Googlers who convinced me (I was skeptical!) that this data-driven approach might work at Google scale.

I joined Google, and we started to retool our translation system toward competing in the NIST Machine Translation Evaluation, a “bake-off” among research institutions and companies to build better machine translation. Google’s massive computing infrastructure and ability to crunch vast sets of web data gave us strong results. This was a major turning point: it underscored how effective the data-driven approach could be.

But at that time our system was too slow to run as a practical service—it took us 40 hours and 1,000 machines to translate 1,000 sentences. So we focused on speed, and a year later our system could translate a sentence in under a second, and with better quality. In early 2006, we rolled out our first languages: Chinese, then Arabic.

We announced our statistical MT approach on April 28, 2006, and in the six years since then we’ve focused primarily on core translation quality and language coverage. We can now translate among any of 64 different languages, including many with a small web presence, such as Bengali, Basque, Swahili, Yiddish, even Esperanto.

Today we have more than 200 million monthly active users on translate.google.com (and even more in other places where you can use Translate, such as Chrome, mobile apps, YouTube, etc.). People also seem eager to access Google Translate on the go (the language barrier is never more acute than when you’re traveling)—we’ve seen our mobile traffic more than quadruple year over year. And our users are truly global: more than 92 percent of our traffic comes from outside the United States.

In a given day we translate roughly as much text as you’d find in 1 million books. To put it another way: what all the professional human translators in the world produce in a year, our system translates in roughly a single day. By this estimate, most of the translation on the planet is now done by Google Translate. (We can’t speak for the galaxy; Douglas Adams’s “Babel fish” probably has us beat there.) Of course, for nuanced or mission-critical translations, nothing beats a human translator—and we believe that as machine translation encourages people to speak their own languages more and carry on more global conversations, translation experts will be more crucial than ever.

We imagine a future where anyone in the world can consume and share any information, no matter what language it’s in, and no matter where it pops up. We already provide translation for webpages on the fly as you browse in Chrome, text in mobile photos, YouTube video captions, and speech-to-speech “conversation mode” on smartphones. We want to knock down the language barrier wherever it trips people up, and we can’t wait to see what the next six years will bring.

Posted by Franz Och, Distinguished Research Scientist, Google Translate

Localize your apps and content more easily — new formats in Translator Toolkit

sergioc — Fri, 30 Mar 2012 15:00:00 +0000

Android Resource (.xml)
Application Resource Bundle (.arb)
Chrome Extension (.json)
GNU gettext-based (.po)

With these new file formats, you can use Translator Toolkit to localize your apps and other products and content much more quickly and easily.

For example, to translate your Android application, go into the res/values directory and upload strings.xml into Translator Toolkit -- Translator Toolkit will now automatically translate it. You can then share your translations with amateur or professional translators, who can localize the text using Translator Toolkit’s WYSIWYG online editor.

When you’re finished, you can export your translated application and store it in a locale-specific directory in Android. Voilà -- easy localization! 翻译起来太方便了!

In addition, we’ve made the Translator Toolkit interface more intuitive for these new file formats so users can translate faster and more accurately. For example, you can turn on ‘Customized colors’ so translators can annotate the edited segments, ‘Number of characters in the segment’ to make sure the text doesn’t run too long (very important for mobile devices), and ‘Synchronized scrolling’ so you can scroll the original and translated text at the same time, which makes navigation much easier.

With these new file formats and UI features, along with the file formats we already support (.aea, .srt, .html), we hope Translator Toolkit can help you reach more users around the world.

When you’re ready, give Google Translator Toolkit a try and suggest any improvements you’d like to see so we can work on making it even better.

Posted by Chris Yang, Product Manager, and Haidong Shao, Software Engineer, Translator Toolkit

Localize your apps and content more easily — new formats in Translator Toolkit

Stephanie Taylor — Fri, 30 Mar 2012 15:00:00 +0000

At Google, we put a lot of energy into helping localize the world’s information to make it more useful to more people. It’s not just about localizing our own products -- we want to provide tools that make it easy for translators and developers around the world to localize their own apps and content. Google Translator Toolkit is our online translation tool for amateur and professional translators -- it’s built on Google Translate and supports more than 100,000 language pairs.

This week, the Translator Toolkit team has launched support for four new translation-related file formats:
• Android Resource (.xml)
• Application Resource Bundle (.arb)
• Chrome Extension (.json)
• GNU gettext-based (.po)

With these new file formats, you can use Translator Toolkit to localize your apps and other products and content much more quickly and easily.

For example, to translate your Android application, go into the res/values directory and upload strings.xml into Translator Toolkit -- Translator Toolkit will now automatically translate it. You can then share your translations with amateur or professional translators, who can localize the text using Translator Toolkit’s WYSIWYG online editor.

When you’re finished, you can export your translated application and store it in a locale-specific directory in Android. Voilà -- easy localization! 翻译起来太方便了!

In addition, we’ve made the Translator Toolkit interface more intuitive for these new file formats so users can translate faster and more accurately. For example, you can turn on ‘Customized colors’ so translators can annotate the edited segments, ‘Number of characters in the segment’ to make sure the text doesn’t run too long (very important for mobile devices), and ‘Synchronized scrolling’ so you can scroll the original and translated text at the same time, which makes navigation much easier.

With these new file formats and UI features, along with the file formats we already support (.aea, .srt, .html), we hope Translator Toolkit can help you reach more users around the world.

When you’re ready, give Google Translator Toolkit a try and suggest any improvements you’d like to see so we can work on making it even better.

Posted by Chris Yang, Product Manager and Haidong Shao, Software Engineer, Translator Toolkit

Using labels in Translator Toolkit

sergioc — Wed, 28 Mar 2012 21:57:00 +0000

Google Translator Toolkit, an online translation tool built on Google Translate, greatly simplifies the translation workflow through its WYSIWYG editor, real-time collaboration and translation management system in the cloud. As amateur translators, we often use Translator Toolkit for projects like translating Wikipedia articles or editing subtitle files for YouTube videos. However, as we work on more and more projects at once, we’ve found we want more powerful ways to organize our Translator Toolkit documents.

So we’re adding labels in Translator Toolkit. We’ve updated them this week, and we thought you’d enjoy a peek at the method to our madness.

With labels, you can organize your Translator Toolkit documents into any categories you define yourself -- ‘high priority,’ ‘wikipedia,’ ‘work,’ ‘later,’ etc. -- and in any combination (the beauty of labels is that they can overlap, so one document might be both ‘work’ and ‘high priority’).

To put a label on a Translator Toolkit document, just select the file and then click ‘Label’ to apply an existing label (or labels). You can also create a new label.

To access all the documents with a given label (or labels), navigate to ‘My labels’ on the left side and choose the labels you’re interested in.

Labels are just one way to make it easier to access and organize your Translator Toolkit documents. Hopefully these changes help you manage more complex projects -- please let us know if you have any feedback.

Posted by Chenjun Wu, Software Engineer, and Chris Yang, Product Manager, Translator Toolkit

Translating patents with the European Patent Office

Jeff — Wed, 29 Feb 2012 18:28:00 +0000

Last March, we signed an agreement with the European Patent Office (EPO) to break down linguistic barriers and improve the machine translation of patents. Today, we’ve released an update to our Google Translate system that incorporates the EPO’s parallel patent texts and allows translation between English and French, German, Spanish, Italian, Portuguese and Swedish.

This improved system is now part of the EPO’s Espacenet service, and goes under the name Patent Translate. Espacenet provides free access to millions of patent documents worldwide - and its users can use Patent Translate to read patents from around the world in their own language. Here’s a video that shows how it works:

Using the EPO’s parallel texts, we’ve been able to improve our ability to translate patents, as the following examples show:

Polymerisable ink

Source: une tête d'impression pour diriger une encre polymérisable par rayonnement vers un substrat reçu sur le support
Old translation: a print head to direct a radiation curable ink to a substrate on the support received
New translation: a print head for directing radiation polymerisable ink to a substrate received on the support

Ultrasonic vibration

Source: The crystals supply the required ultrasonic vibration needed to drive both the horn and the attached cutting tip during phacoemulsification and are controlled by the console.
Old translation: I cristalli di fornire la vibrazione necessaria ad ultrasuoni necessari per guidare sia il corno e la punta di sezionamento annesso durante facoemulsificazione e sono controllati dalla console.
New translation: I cristalli forniscono la vibrazione ultrasonica richiesta necessaria per pilotare sia il corno e la punta da taglio allegata durante la facoemulsificazione e sono controllati dalla console.

We share a similar vision to the EPO, that machine translation can help to overcome language barriers - and help to make the information contained in patents universally accessible and useful. While the improved system is pretty good, machine translation is a challenging computer science problem and does not always deliver perfect results. But it can be a very useful way for people to search and read patents that aren’t written in their language.

We’re excited to continue our collaboration with the EPO. We look forward to adding more languages - and showing how this public-private partnership will further improve access to patents for people around the world.

Posted by Jeff Chin, Product Manager, Google Translate

An easier way to type in Japanese, Vietnamese, and Hebrew

Edeguine — Mon, 27 Feb 2012 18:30:00 +0000

Knowing what you want to translate is sometimes only half the battle. You may have a letter from your secret admirer sitting in front of you, but if you can’t type the words into Google Translate the meaning can remain elusive.

Typing in languages which use different character sets can be a frustrating problem in computer labs, internet cafés, and sometimes even on home computers if standard Latin alphabet keyboards are the only option available.

To make typing in these languages easier we began including virtual keyboards and transliteration input methods in Google Translate last year, and we’ve been working to expand that support over time. Today we’re happy to announce three major additions to our input methods: Japanese, Vietnamese, and Hebrew language support.

To use transliteration input methods, just select the ‘Allow phonetic typing’ option when typing in Google Translate.
Since releasing transliteration support for these languages a few days ago, we’ve noticed significant improvements in the the speed of input (for instance, Vietnamese text input has become 20% faster with the new input method) which we hope to see translate into a better experience for everyone.

Keep an eye out over the next few months as we add support for more languages.

Would you like to use Google’s transliteration input methods or virtual keyboards across the whole web? Try out our Chrome extension, which includes transliteration for over 20 languages and virtual keyboards for 70 more.

Posted by C. Andrew Warren, Associate Product Manager, Internationalization Team

Tutmonda helplingvo por ĉiuj homoj

Nadja Blagojevic — Wed, 22 Feb 2012 21:35:00 +0000

Today, we are adding Esperanto to Google Translate, making it our 64th supported language.

Ludovic Lazarus Zamenhof started his quest for an easy-to-learn language shared by all people in the 1870s and first published the ideas in 1887 with his book Unua Libro. The concept of a common language spread quickly, and initial reactions to Esperanto have ranged from suppression to enthusiastic embrace. Now, 125 years later, Esperanto has hundreds of thousands of active speakers, millions of people with some knowledge of the language, and even a few hundred people who learned it from birth, taught by their parents.

Esperanto and Google Translate share the goal of helping people understand each other, this connection has been made even in this blog post. Therefore, we are very excited that we can now offer translation for this language as well.

The Google Translate team was actually surprised about the high quality of machine translation for Esperanto. As we know from many experiments, more training data (which in our case means more existing translations) tends to yield better translations. For Esperanto, the number of existing translations is comparatively small. German or Spanish, for example, have more than 100 times the data; other languages on which we focus our research efforts have similar amounts of data as Esperanto but don’t achieve comparable quality yet. Esperanto was constructed such that it is easy to learn for humans, and this seems to help automatic translation as well.

Although the system is still far from perfect, we hope that our latest addition helps you to learn more about Esperanto’s history and culture. Translation to and from Esperanto will soon be available on translate.google.com, in our mobile web app, and in the Google Translate app for Android and iOS.

Posted by Thorsten Brants, Research Scientist, Google Translate

Sometimes it’s easier just to write it

Edeguine — Wed, 04 Jan 2012 23:32:00 +0000

With our most recent update to Google Translate for Android, we’ve added an experimental new input feature: handwriting on your touchscreen.

Maybe you’d like to see if three 木 make a 森, but you don’t have a Japanese keyboard installed? Just use the handwriting icon

Our goal is to break down the language barrier, all the time, everywhere. By adding handwriting input directly into our Android app we hope to help you get translation done even more quickly and easily. Sometimes you don’t know how to say what you want translated, sometimes you can’t type it, and sometimes it’s easier just to write it. We think of handwriting on the touchscreen as another natural input that you may want to use to complement the keyboard, microphone, or camera.

This is still an experimental feature. It’s available in Chinese and Japanese, and you can enable it for English, French, Italian, German, and Spanish if you like. (We currently only support single-character input for Chinese and Japanese.) Just as with speech recognition and our translations themselves, our handwriting recognition happens in the cloud, allowing us to continually improve accuracy without requiring you to download new versions of the app.

Download Google Translate in Android Market — it’s available for tablets and mobile phones running Android 1.5 and up. Then, you can easily find out whether 自 really means ‘server rack with a Wi-Fi antenna’.

Posted by Daniel Keysers, Software Engineer

Translate more Indic languages with the updated Google Translate for iPhone app

Jeff — Fri, 04 Nov 2011 00:15:00 +0000

Back in June, we launched five new experimental Indic languages for Google Translate on the desktop and mobile web app. Today, we’ve updated the Google Translate for iPhone app to add these new alpha languages: Bengali, Gujarati, Kannada, Tamil and Telugu. This brings the total number of languages supported by the app to 63 languages.

The updated app supports the ability to view dictionary results for single words and to display romanizations for these new Indic languages. So even if you can't read the script the words are written in, you can still take a shot at reading the translation.

Since these are still experimental alpha languages, you can expect translations be less fluent and include many more untranslated words than some of our more mature languages—like Spanish or Chinese—which have much more parallel data to power our statistical machine translation approach. Despite these challenges, we believe users will find these new languages helpful and we're excited to be making them available through the Translate app.

Google Translate for iPhone now supports text translation among 63 languages, voice input in 17 of those languages, and text-to-speech in 24 of them. Get the latest version of the Google Translate for iPhone app from the App Store now and start breaking down language barriers wherever you are!

Posted by Jeff Chin, Product Manager, Google Translate

Breaking down language barriers with translated English-language results

Jeff — Tue, 25 Oct 2011 18:02:00 +0000

(Cross-posted from the Inside Search Blog)

English speakers take it for granted that they can always find answers online, regardless of their search topic. But what if you speak Hindi, Welsh or Afrikaans? The amount of content available online per speaker for Hindi is just 1% of the vast content out there on the web per English speaker. So if you speak one of the languages with less online content, some of the most relevant results for your search may actually be in English.

To help break down that language barrier between you and the answers you need, starting today you may see relevant results in English in addition to those in your default language. For example, let’s say you speak Hindi and want to find information on mountain climbing -- we want to help you also find the relevant pages in English and for these, you’ll also see a translation into your language.

Language is one of the biggest barriers to making information universally accessible, and we’ve been working to make increasing use of machine translation to improve search across languages. This is especially important for languages with less prevalent local language content available online. You should also get the most relevant information regardless of the language you’re searching in. We use machine translation to translate your search, find the pages that best answer your question and translate the relevant results for you.

You’ll start to see relevant English-language pages when you’re searching in one of 14 languages: Afrikaans, Malay, Swahili, Serbian, Slovak, Macedonian, Slovenian, Norwegian, Hindi, Catalan, Maltese, Icelandic, Welsh and Albanian. If you click on the main result title, you’ll get to the original English-language page, while the translated link underneath will take you to a translated page. We hope this will help you find the information you need, no matter what language it’s in.

Posted by Jordan Gilliland, Software Engineer - Cross Language Search Team

Bringing relevant news to you, regardless of language — translated news

sergioc — Tue, 25 Oct 2011 17:48:00 +0000

To help bridge language barriers between you and the news of interest to you from around the world -- and to bring you more diverse perspectives on foreign events -- we’ve added a new “translate” button to the expandable story boxes in the U.S. English edition of Google News.

Clicking the translate button reveals the English translation of the original headline using Google Translate. Clicking on the headline takes you to the publisher’s website where you can choose to use Google Translate to see an English version of the entire article. Headlines are labeled with their country of origin.

To do this, we look for foreign articles from local sources on a relevant news topic. For example, in the case of the flood in Thailand, in addition to surfacing English articles from international press like New York Times, we might show a related article from a local source like อาร์วายที9.

At the same time, we hope readers will benefit from finding relevant news in other languages and being able to read it without knowing the language.

Posted by Yaroslav Kurovtsev, Software Engineer, Google Translate

Start the conversation with Google Translate for Android

Jeff — Thu, 13 Oct 2011 20:07:00 +0000

(Cross posted on the Official Google Blog and Google Mobile Blog)

Mobile technology and the web have made it easier for people around the world to access information and communicate with each other. But there’s still a daunting obstacle: the language barrier. We’re trying to knock down that barrier so everyone can communicate and connect more easily.

Earlier this year, we launched an update to Google Translate for Android with an experimental feature called Conversation Mode, which enables you to you translate speech back and forth between languages. We began with just English and Spanish, but today we’re expanding to 14 languages, adding Brazilian Portuguese, Czech, Dutch, French, German, Italian, Japanese, Korean, Mandarin Chinese, Polish, Russian and Turkish.

To use Conversation Mode, speak into your phone’s microphone, and the Translate app will translate what you’ve said and read the translation out loud. The person you’re speaking with can then reply in their language, and Conversation Mode will translate what they said and read it back to you.

This technology is still in alpha, so factors like background noise and regional accents may affect accuracy. But since it depends on examples to learn, the quality will improve as people use it more. We wanted to get this early version out to help start the conversation no matter where you are in the world.

We’ve also added some other features to make it easier to speak and read as you translate. For example, if you wanted to say “Where is the train?” but Google Translate recognizes your speech as “Where is the rain?”, you can now correct the text before you translate it. You can also add unrecognized words to your personal dictionary.

When viewing written translation results, you can tap the magnifying glass icon to view the translated text in full screen mode so you can easily show it to someone nearby, or just pinch to zoom in for a close-up view.

Tap the magnifying glass icon to view translations full screen.

Finally, we’ve also optimized the app for larger screens like your Android tablet.

While we work to expand full Conversation Mode to even more languages, Google Translate for Android still supports text translation among 63 languages, voice input in 17 of those languages, and text-to-speech in 24 of them.

Download the Google Translate app in Android Market — it’s available for tablets and mobile phones running Android 2.2 and up.

Posted by Jeff Chin, Product Manager

Start the conversation with Google Translate for Android

dly — Thu, 13 Oct 2011 08:07:00 +0000

(Cross posted on the Official Google Blog and Google Translate Blog)

Tap the magnifying glass icon to view translations full screen.

Google Translate for Google+

Jeff — Mon, 29 Aug 2011 23:39:00 +0000

We've heard from a lot of Google+ users wanting an easier way to understand posts written in other languages, so we thought we should do something about that.

We just introduced on Google+, a new Chrome extension, Google Translate for Google+, that uses the power of Google Translate to automatically translate any post or comment into more than 50 languages.

Once you've installed the extension, refresh Google+ and you'll see Translate links next to posts and comments. Click the links to instantly see translations.

You can get the extension from the Chrome Web Store here:
https://chrome.google.com/webstore/detail/jfppgkomfopklagggkjiaddgndkgopgl

Note: This extension is currently experimental as we figure out the best way to integrate translation into the Google+ community. So please give us your feedback in the comments, or by clicking the “Send Feedback” button on Google+.

Posted by Josh Estelle, Senior Software Engineer

Paid version of Google Translate API now open for business

Jeff — Wed, 24 Aug 2011 21:00:00 +0000

(Cross-posted from the Google Code Blog)

Back in May, we announced the deprecation of the free Translate API v1. Today, we’re introducing a paid version of the Google Translate API for businesses and commercial software developers. The Google Translate API provides a programmatic interface to access Google’s latest machine translation technology. This API supports translations between 50+ languages (more than 2500 language pairs) and is made possible by Google’s cloud infrastructure and large scale machine learning algorithms.

The paid version of Translate API removes many of the usage restrictions of previous versions and can now be used in commercial products. Translation costs $20 per million (M) characters of text translated (or approximately $0.05/page, assuming 500 words/page). You can sign up online via the APIs console for usage up to 50 M chars/month.

Developers who created projects in the APIs Console and started using the Translate API v2 prior to today will continue to receive a courtesy limit of 100K chars/day until December 1, 2011 or until they enable billing for their projects.

For academic users, we will continue to offer free access to the Google Translate Research API through our University Research Program for Google Translate. For website translations, we encourage you to use the Google Website Translator gadget which will continue to be free for use on all web sites. In addition, Google Translate, Translator Toolkit, the mobile translate apps for iPhone and Android, and translation features within Chrome, Gmail, etc. will continue to be available to all users at no charge.

Posted by Jeff Chin, Product Manager

Messages for Japan at Tanabata in Sendai

AV — Mon, 15 Aug 2011 22:55:00 +0000

(Cross-posted from the Official Google Blog)

A month after this spring’s devastating earthquake in Japan, we created a site where people from around the world could submit messages of hope in their own languages and have them automatically translated into Japanese. From Paris to Dubai to Manila, nearly 30,000 messages have been posted through messagesforjapan.com.

This past weekend marked the celebration of Tanabata in Sendai, the largest city in the disaster area and home to one of the most famous festivals in the country. People often celebrate Tanabata, which means "Evening of the Seventh,” by writing wishes on tanzaku (small strips of paper) and hanging them on bamboo branches. This year, these paper strips displayed some of the messages of hope submitted through the site, and festival participants added their own messages to those from around the world.

We’ve updated messagesforjapan.com so you can see photos of people gathering for Tanabata in Sendai—reading, creating and hanging messages in the area surrounding the disaster earlier this year.

Posted by Arielle Reinstein, Product Marketing Manager

Google Goggles learns Russian and gets a new view

Julie Z — Wed, 22 Jun 2011 16:15:00 +0000

Some of you may already be using the new optical character recognition (OCR) and translation of Russian in Google Goggles that we previewed at last week’s Inside Search event. Starting today, we’re pleased to introduce some additional new features, including a map view of your Search History and the ability to copy contact and text results to the clipboard. We’ve also changed the results interface to make it easier to view and navigate through your results.

Russian optical character recognition (OCR) and translation
Since Google Goggles first launched in 2009, it has been able to recognize and translate text in a number of different languages, as long as the language used Latin characters. With the launch of OCR for Russian, Goggles is now able to read Cyrillic characters. Goggles will recognize a picture of Russian text and allow you to translate the text into one of over 40 other languages. Russian OCR is also available for users of Google Goggles on the Google Search app for iOS. Очень полезно!

You can take a picture of Russian text and translate it into over 40 languages.

Map view of your search history
If you’ve enabled search history on Goggles, your history contains a list of all the images that you’ve searched for, as well as some information about where you performed the search if you chose to share your location with Google. Sometimes this can be a pretty long list, so we wanted to give you another way to sort and visualize your Goggles results.

We’ve added a map view, which shows your Goggles image search history on a map so you can quickly zoom and pan to find a query from a particular location.

Easily toggle between map view and list view with the button in the upper right.

Copy contact and text results to clipboard
Finally, imagine that you wanted to grab a URL or telephone number from a sign and email it to yourself. Now, Goggles gives you the option of copying the recognized text to your phone’s clipboard, allowing you to paste the test into a number of applications.

To try these new features download Google Goggles 1.5 from Android Market, or scan the QR code below with your phone.

Posted by George Nachman, Software Engineer