Category Archives: Google Translate Blog

The official source of information about our translation and language technologies

Making the internet more inclusive in India

More than 400 million people in India use the internet, and more are coming online every day. But the vast majority of India’s online content is in English, which only 20 percent of the country’s population speaks—meaning most Indians have a hard time finding content and services in their language.

Building for everyone means first and foremost making things work in the languages people speak. That’s why we’ve now brought our new neural machine translation technology to translations between English and nine widely used Indian languages—Hindi, Bengali, Marathi, Gujarati, Punjabi, Tamil, Telugu, Malayalam and Kannada.

Neural machine translation translates full sentences at a time, instead of pieces of a sentence, using this broader context to help it figure out the most relevant translation. The result is higher-quality, more human sounding translations.

Just like it’s easier to learn a language when you already know a related language, our neural technology speaks each language better when it learns several at a time. For example, we have a whole lot more sample data for Hindi than its relatives Marathi and Bengali, but when we train them all together, the translations for all improve more than if we’d trained each individually.

NMT Translation India.jpg
Left: Phrase-based translation; right: neural machine translation

These improvements to Google Translate in India join several other updates we announced at an event in New Delhi today, including neutral machine translation in Chrome and bringing the Rajpal & Sons Hindi dictionary online so it’s easier for Hindi speakers to find word meanings right in search results. All these improvements help make the web more useful for hundreds of millions of Indians, and bring them closer to benefiting from the full value of the internet.

Source: Translate


Even better translations in Chrome, with one tap

Half the world’s webpages are in English, but less than 15 percent of the global population speaks it as a primary or secondary language. It’s no surprise that Chrome’s built-in Translate functionality is one of the most beloved Chrome features. Every day Chrome users translate more than 150 million webpages with just one click or tap.

Last year, Google Translate introduced neural machine translation, which uses deep neural networks to translate entire sentences, rather than just phrases, to figure out the most relevant translation. Since then we’ve been gradually making these improvements available for Chrome’s built-in translation for select language pairs. The result is higher-quality, full-page translations that are more accurate and easier to read.

Today, neural machine translation improvement is coming to Translate in Chrome for nine more language pairs. Neural machine translation will be used for most pages to and from English for Indonesian and eight Indian languages: Bengali, Gujarati, Kannada, Malayalam, Marathi, Punjabi, Tamil and Telugu. This means higher quality translations on pages containing everything from song lyrics to news articles to cricket discussions.
translation.png
From left: A webpage in Indonesian; the page translated into English without neural machine translation; the page translated into English with neural machine translation. As you can see, the translations after neural machine translation are more fluid and natural.

The addition of these nine languages brings the total number of languages enabled with neural machine translations in Chrome to more than 20. You can already translate to and from English for Chinese, French, German, Hebrew, Hindi, Japanese, Korean, Portuguese, Thai, Turkish, Vietnamese, and one-way from Spanish to English.

We’ll bring neural machine translation to even more languages in the future. Until then, learn more about enabling Translate in Chrome in our help center.

Source: Translate


The Arrival of our 32nd Word Lens Language, Heptapod B

We’re honored to have partnered with Dr. Louise Banks, esteemed linguistics professor, to develop instant camera translation for our 32nd language, Heptapod B. Following our experience with logograms in Chinese and Japanese, as well as the many characters containing circles in Korean, we were ready to blend our expertise in low-memory-footprint convolutional modeling and Dr. Banks’ linguistic background to the deciphering of circular logograms in the Word Lens feature in the Google Translate app.

Translate_Arrival_1.png

The challenge with understanding Heptapod B is its nonlinear orthography. Fortunately, Google's neural machine translation system employs an encoder/decoder system that internally represents sentences as high-dimensional vectors. These vectors map well to the non-linear orthography of the Heptapod language and they are really the enabling technical factor in translating Heptapod B.

We interpret Heptapod B into English, Chinese, Danish, Japanese, Urdu, Russian, French, Spanish and Arabic. As with our other Word Lens languages, it works offline, which is really handy if you happen to need to read a circular logogram in an isolated location. Dr. Banks assures us that the app will continue to work for at least 3,000 years.

Translate_Arrival_2.png

Communicating across language (and glass) barriers can be a rather alienating experience. While learning a new writing system can be quite rewarding and even a mind-altering experience, not everyone has time for that. So whether the world’s fate hangs in the balance, or if you’re simply trying to discern whether your coffee stain ring means something, we wish you success as you integrate this tool into the story of your life.

Source: Translate


The Arrival of our 32nd Word Lens Language, Heptapod B

We’re honored to have partnered with Dr. Louise Banks, esteemed linguistics professor, to develop instant camera translation for our 32nd language, Heptapod B. Following our experience with logograms in Chinese and Japanese, as well as the many characters containing circles in Korean, we were ready to blend our expertise in low-memory-footprint convolutional modeling and Dr. Banks’ linguistic background to the deciphering of circular logograms in the Word Lens feature in the Google Translate app.

Translate_Arrival_1.png

The challenge with understanding Heptapod B is its nonlinear orthography. Fortunately, Google's neural machine translation system employs an encoder/decoder system that internally represents sentences as high-dimensional vectors. These vectors map well to the non-linear orthography of the Heptapod language and they are really the enabling technical factor in translating Heptapod B.

We interpret Heptapod B into English, Chinese, Danish, Japanese, Urdu, Russian, French, Spanish and Arabic. As with our other Word Lens languages, it works offline, which is really handy if you happen to need to read a circular logogram in an isolated location. Dr. Banks assures us that the app will continue to work for at least 3,000 years.

Translate_Arrival_2.png

Communicating across language (and glass) barriers can be a rather alienating experience. While learning a new writing system can be quite rewarding and even a mind-altering experience, not everyone has time for that. So whether the world’s fate hangs in the balance, or if you’re simply trying to discern whether your coffee stain ring means something, we wish you success as you integrate this tool into the story of your life.

(Okay, if you haven’t guessed already... we’re just having some fun here. But we really are eager to bring Word Lens and Neural translation to more languages,
so stay tuned.)

Source: Translate


How Google Translate is making learning English fun in Israel

Using neural machine translation, we’ve just updated Hebrew and Arabic languages on Google Translate. But what you can’t see on the surface is that these translations also improved thanks to students across Israel. As English as a Foreign Language (EFL) students used the Google Translate Community platform to learn and practice their English, they actually improved translations for everyone in the process.

Adele Raemer is an Israeli English teacher, a trainer for English as a Foreign Language (EFL) and digital pedagogy at the Israel Ministry of Education; she’s also a Google Certified Innovator, a Google Educator Group leader, and blogger.

Adele Raemer.png
Adele Raemer, English as a Foreign Language teacher and trainer at Israel’s Ministry of Education

When Adele first used the Translate Community as tool to teach English, she was impressed by how eager and motivated her students became. She wanted other students to share in the experience, so with the support of the Ministry of Education EFL superintendent and our education team, she turned this into a challenge for classrooms across Israel. The goal was to help students work on their vocabulary, develop critical thinking and translating skills and enhanced their engagement with English studies.

Last spring, 51 classes from across the country joined our Google Translate Community pilot competition. A month later, the class with the highest number of collective contributions joined us for a visit to our Google Israel office. The teachers used the challenge as a fun activity on top of their regular curriculum. As Mazi, an English teacher at “Hodayot” high school, said: “The experience of participating in the competition was very positive and enriched my teaching. Any time that a student finished a task early or had a bit of time at the end of the lesson, they could be productive by going into the site and translating!”

Translate_Israel_Group.png
Winning class from Jadeidi-Makr science school who won a visit to the Google Israel office

Inspired by the success of Adele's pilot program, the Translate Community team then built new tools that allowed group contributions and measured results more accurately. With new supporting lesson plans, more than 150 classes participated in a three month competition for Hebrew-English and Arabic-English. From these two competitions, 3,500 students translated and verified more than 4 million words and phrases.

Translate_Israel_1.png
English teacher from the winning school, “Nitzanim” school, with a student translating during a lesson

We’ve incorporated this multi-lingual knowledge into the training for our cutting-edge neural technology, which we’ve just launched today for Hebrew and Arabic. That means every one of these contributions helped improve translations for millions of people doing translations to or from these related languages.

We were thrilled to see the great impact that these students had on Translate itself. It’s so cool to see how the next generation of students is working hand in hand with the next generation of machine translation technology!

Source: Translate


How Google Translate is making learning English fun in Israel

Using neural machine translation, we’ve just updated Hebrew and Arabic languages on Google Translate. But what you can’t see on the surface is that these translations also improved thanks to students across Israel. As English as a Foreign Language (EFL) students used the Google Translate Community platform to learn and practice their English, they actually improved translations for everyone in the process.

Adele Raemer is an Israeli English teacher, a trainer for English as a Foreign Language (EFL) and digital pedagogy at the Israel Ministry of Education; she’s also a Google Certified Innovator, a Google Educator Group leader, and blogger.

When Adele first used the Translate Community as tool to teach English, she was impressed by how eager and motivated her students became. She wanted other students to share in the experience, so with the support of the Ministry of Education EFL superintendent and our education team, she turned this into a challenge for classrooms across Israel. The goal was to help students work on their vocabulary, develop critical thinking and translating skills and enhanced their engagement with English studies.

Last spring, 51 classes from across the country joined our Google Translate Community pilot competition. A month later, the class with the highest number of collective contributions joined us for a visit to our Google Israel office. The teachers used the challenge as a fun activity on top of their regular curriculum. As Mazi, an English teacher at “Hodayot” high school, said: “The experience of participating in the competition was very positive and enriched my teaching. Any time that a student finished a task early or had a bit of time at the end of the lesson, they could be productive by going into the site and translating!”

Translate_Israel_Group.png
Winning class from Jadeidi-Makr science school who won a visit to the Google Israel office

Inspired by the success of Adele's pilot program, the Translate Community team then built new tools that allowed group contributions and measured results more accurately. With new supporting lesson plans, more than 150 classes participated in a three month competition for Hebrew-English and Arabic-English. From these two competitions, 3,500 students translated and verified more than 4 million words and phrases.

We’ve incorporated this multi-lingual knowledge into the training for our cutting-edge neural technology, which we’ve just launched today for Hebrew and Arabic. That means every one of these contributions helped improve translations for millions of people doing translations to or from these related languages.

We were thrilled to see the great impact that these students had on Translate itself. It’s so cool to see how the next generation of students is working hand in hand with the next generation of machine translation technology!

Source: Translate


Higher quality neural translations for a bunch more languages

Last November, people from Brazil to Turkey to Japan discovered that Google Translate for their language was suddenly more accurate and easier to understand. That’s because we introduced neural machine translation—using deep neural networks to translate entire sentences, rather than just phrases—for eight languages overall. Over the next couple of weeks, these improvements are coming to Google Translate in many more languages, starting right now with Hindi, Russian and Vietnamese.

Neural translation is a lot better than our previous technology, because we translate whole sentences at a time, instead of pieces of a sentence. (Of course there’s lots of machine learning magic powering this under the hood, which you can read about on the Research blog.) This makes for translations that are usually more accurate and sound closer to the way people speak the language. Here’s one example to show how much it’s improved:

You’ll get these new translations automatically in most places Google Translate is available: in the iOS and Android apps, at translate.google.com, and through Google Search and the Google app. We’ll be introducing neural machine translation to even more languages over the next few weeks, so keep an eye out for smoother, more fluent translations.

Finally, please keep contributing to Translate Community! Our translations are still far from perfect, and it helps everyone using Google Translate when you suggest improvements.

Source: Translate


Higher quality neural translations for a bunch more languages

Last November, people from Brazil to Turkey to Japan discovered that Google Translate for their language was suddenly more accurate and easier to understand. That’s because we introduced neural machine translation—using deep neural networks to translate entire sentences, rather than just phrases—for eight languages overall. Over the next couple of weeks, these improvements are coming to Google Translate in many more languages, starting right now with Hindi, Russian and Vietnamese.

Neural translation is a lot better than our previous technology, because we translate whole sentences at a time, instead of pieces of a sentence. (Of course there’s lots of machine learning magic powering this under the hood, which you can read about on the Research blog.) This makes for translations that are usually more accurate and sound closer to the way people speak the language. Here’s one example to show how much it’s improved:

hindi translate

You’ll get these new translations automatically in most places Google Translate is available: in the iOS and Android apps, at translate.google.com, and through Google Search and the Google app. We’ll be introducing neural machine translation to even more languages over the next few weeks, so keep an eye out for smoother, more fluent translations.

Finally, please keep contributing to Translate Community! Our translations are still far from perfect, and it helps everyone using Google Translate when you suggest improvements.

Source: Translate


Higher quality neural translations for a bunch more languages

Last November, people from Brazil to Turkey to Japan discovered that Google Translate for their language was suddenly more accurate and easier to understand. That’s because we introduced neural machine translation—using deep neural networks to translate entire sentences, rather than just phrases—for eight languages overall. Over the next couple of weeks, these improvements are coming to Google Translate in many more languages, starting right now with Hindi, Russian and Vietnamese.

Neural translation is a lot better than our previous technology, because we translate whole sentences at a time, instead of pieces of a sentence. (Of course there’s lots of machine learning magic powering this under the hood, which you can read about on the Research blog.) This makes for translations that are usually more accurate and sound closer to the way people speak the language. Here’s one example to show how much it’s improved:

Hindi_GoogleTranslate_v4_Blog.gif

You’ll get these new translations automatically in most places Google Translate is available: in the iOS and Android apps, at translate.google.com, and through Google Search and the Google app. We’ll be introducing neural machine translation to even more languages over the next few weeks, so keep an eye out for smoother, more fluent translations.

Finally, please keep contributing to Translate Community! Our translations are still far from perfect, and it helps everyone using Google Translate when you suggest improvements.

Source: Translate


Higher quality neural translations for a bunch more languages

Last November, people from Brazil to Turkey to Japan discovered that Google Translate for their language was suddenly more accurate and easier to understand. That’s because we introduced neural machine translation—using deep neural networks to translate entire sentences, rather than just phrases—for eight languages overall. Over the next couple of weeks, these improvements are coming to Google Translate in many more languages, starting right now with Hindi, Russian and Vietnamese.

Neural translation is a lot better than our previous technology, because we translate whole sentences at a time, instead of pieces of a sentence. (Of course there’s lots of machine learning magic powering this under the hood, which you can read about on the Research blog.) This makes for translations that are usually more accurate and sound closer to the way people speak the language. Here’s one example to show how much it’s improved:

Hindi_GoogleTranslate_v4_Blog.gif

You’ll get these new translations automatically in most places Google Translate is available: in the iOS and Android apps, at translate.google.com, and through Google Search and the Google app. We’ll be introducing neural machine translation to even more languages over the next few weeks, so keep an eye out for smoother, more fluent translations.

Finally, please keep contributing to Translate Community! Our translations are still far from perfect, and it helps everyone using Google Translate when you suggest improvements.

Source: Translate