Yandex Blog

Yandex.Taxi’s Self-Driving Car Conducts Winter Testing on Moscow’s Public Streets

Last week the Yandex.Taxi driverless car team passed another major milestone on our mission to achieve a level 5 self-driving car, which began with the May 2017 prototype launch.  The Yandex.Taxi autonomous car safely navigated the streets of Moscow after a recent snowstorm managing interactions with traffic, pedestrians, parked vehicles and other road hazards on snowy and icy streets. The drive, which occurred during light precipitation and -6 C (21 F) temperatures, was an advanced test challenging the vehicle with winter weather conditions on public roads.

Over the last few months the team has been testing prototypes in winter weather conditions on a closed course near Moscow.  In December 2017, the team debuted the car on public roads and began collecting data during public street testing to further advance Yandex’s driverless technology.

Navigating snow-covered city streets requires significant amounts of data including images of both the snowy roads and street signs.  Moscow offers our team a great testing ground for our self-driving car, challenging it with both high traffic volumes and diverse weather and seasonal changes.  

Our journey with our self-driving car began less than a year ago on closed testing grounds and dry weather conditions. Today we are excited to have advanced our technology to safely navigate the challenges of public streets and winter weather.

We will continue to test our self-driving cars on public roads, collecting more data to make our technology smarter and more reliable. It’s our goal to expand our capabilities to create a universally applicable technology that manages all road challenges and weather conditions. 

Yandex’s Seventh Annual Programming Competition Yandex.Algorithm Starts This Week

Since 2011 Yandex has been running a programming competition, Yandex.Algorithm, to challenge competitive coders and advance the machine learning community. Yandex.Algorithm welcomes coding contestants from around the world to enter up to three tracks of the 2018 competition: algorithm track, optimization track, and ML track. 

Each track was designed to test contestants with a variety of problem solving tasks. Historically, Yandex.Algorithm has focused on the algorithm track but last year it included more diverse problems such as optimization tasks.  Following positive feedback from the community on these changes, we designed the Yandex.Algorithm 2018 competition to include optimization and machine learning problems within separate applied science tracks.

The algorithm track is designed to follow its traditional format in which submitted solutions are run against test cases. The optimization track was developed with the help of our search algorithm engineers and our autonomous vehicle team members to require a multitude of creative approaches rather than a single solution. The optimization track answers will be evaluated and awarded points based on the test performances of submitted solutions. The machine learning track tasks require contestants to create models, which will be evaluated based on how well specified parameters can be predicted using the models.

Yandex.Algorithm contestants are competing to advance their programming capabilities in addition to cash prizes.  The winner of the algorithmic track will take home approximately a $5000 cash prize and the second and third place winners will receive $2600 and $1600 respectively.  The winners in the other two categories will each receive approximately $1800 and runners up in these new tracks will also be awarded cash prizes as well.  Over 500 of the top performing participants will receive a Yandex.Algorithm t-shirt.

The three tracks will run consecutively in order to give all participants the opportunity to try their hand at solving every type of a problem in the Yandex.Algorithm 2018 competition. The first qualification round for the algorithmic track will take place on February 17th. The 25 best performers in the three qualifying rounds of the algorithmic track will be invited to Saint Petersburg on May 19th for the finals.  The optimization track and the machine learning track will run online competitions starting in March.

Interested programmers can register and find all relevant information for Yandex.Algorithm in both English and Russian on the competition website.  Congratulations to the 2017 winner, Gennady Korotkevich, a Belarusian information technology student from Saint Petersburg, who has won the top Yandex.Algorithm prize four times! Good luck to all of the 2018 participants!

Yandex Improves Browsing Experience With Native Ad Blocking in Yandex Browser

At Yandex our mission is to help consumers and businesses better navigate the online and offline world.  And when it comes to digital advertising this means working to make the Internet a place where users have enjoyable high-quality experiences and businesses can reach their audiences in effective ways.

As part of this work, today Yandex introduced native ad blocking in the Russian version of Yandex Browser to enhance users’ browsing experience by filtering intrusive advertising. The latest browser update includes a built-in ad blocker that prevents annoying or disruptive ads from loading when a page is displayed to the user. The built-in ad blocker is activated by default both in the desktop and mobile versions of Yandex Browser but can be deactivated in the settings.

Yandex Browser now blocks full-screen banner ads, pop-ups with a countdown timer, autoplay video ads and other formats of unwanted advertising, or those that do not comply with new advertising guidelines announced by the Russian branch of the Interactive Advertising Bureau (IAB) last month. Relevant ads in non-intrusive, organic formats will still be displayed to the user. 

Organizations like IAB Russia have worked to better understand which forms of advertising are hindering users’ online experience by conducting consumer driven research.  As an active member of IAB Russia, we value and support their work towards understanding what users want and developing higher quality advertising that leads to a beneficial experience for both users and publishers.

“At Yandex we believe in building an enjoyable online experience in which people are delivered helpful information. Aggressive advertising interferes with a high-quality user experience and has led to increased ad blocker downloads, which can block potentially useful offers and information to users,” says Dmitry Timko, head of Yandex Browser. “Native ad blocking eliminates the need for additional ad blockers and promotes better quality advertising.”

Yandex Browser has long been committed to delivering high-quality user experiences and protecting web audiences. In 2014, Yandex Browser integrated built-in Antishock technology that blocks malicious and fraudulent advertising. In 2016, Yandex Browser started offering users comprehensive fraud protection against the majority of online threats through Protect,  a built-in cyber security system. Protect automatically checks all downloaded files for viruses, warns users about dangerous websites, protects users’ passwords when using public networks, and ensures safe payments.

In order to help publishers and advertisers continue to create effective ads and follow the new guidelines, we introduced a ‘Diagnostics’ tool available on the Yandex.Webmaster service, where publishers and advertisers can check if their advertising is compliant with Yandex standards.

As the provider of the second most popular browser in Russia and a member of IAB Russia, today is an important day for advancements in digital advertising for Yandex and the entire RuNet.

Yandex Partners with Tel Aviv University to Enhance AI Education

Yandex is thrilled to partner with Tel Aviv University (TAU) to create the Yandex Machine Learning Initiative and open the sixth branch of the Yandex School of Data Analysis (YSDA), where a new career advancement program will be offered.

From digital learning platforms to our master’s program, Yandex has led several major education initiatives to improve the development and impact of AI in both academia and the private sector over the last decade. Our new partnership with TAU marks a key step in expanding our machine learning education and innovation programs to one of the world’s leading tech centers.

Today the tech community in Israel hosts many of the top startups creating innovative products and services that are shaping the future of AI globally.  As the largest university in Israel, TAU plays a critical role in the development of both the local and global tech community. The team at TAU provides a world-class computer science education and shares our vision to enhance the global AI ecosystem by creating more experts and innovators in the field.  Yandex CEO, Arkady Volozh, who spearheaded the partnership explains, “It’s our goal to not only ensure education in AI continues to grow the global community but also to keep challenging and advancing our ability to shape the future of AI.”  

The Yandex Machine Learning Initiative will be run through TAU’s Blavatnik School of Computer Science as part of the BSc Program in Computer Science. The program will introduce a cluster of courses that will focus on machine learning, deep learning, natural language processing, computer vision and robotics.

The majority of the initiative will be dedicated to expanding opportunities for students through Yandex Fellowships, which will award scholarships to the brightest students at the master’s, doctoral, and post-doctoral level.  As part of the initiative, the Yandex International Distinguished Lecture Series in Machine Learning will enhance collaboration by bringing experts from around the world to TAU to give lectures and conduct research with TAU faculty.  Furthermore, the Yandex Initiative will also support new faculty recruitment and the acquisition of state-of-the-art equipment to enhance the program.

In addition to the Yandex Machine Learning Initiative at the university, TAU will become the sixth campus location of the Yandex School of Data Analysis (YSDA), where YSDA will launch a one-year career advancement program for the first time.  For over ten years now, YSDA has been offering a master’s level program in Computer Science and Data Analysis that challenges students with two vigorous years of training from top experts in the most advanced data science topics.  To date, over 600 YSDA graduates have brought their understanding of theoretical foundations and hands-on experience at YSDA to academia and leading technology companies around the world. 

While the majority of YSDA graduates have gone on to work at companies like Yandex, Microsoft, and Apple, the future of AI is not limited to tech companies and academia but will continue to expand into a wide range of industries and businesses where machine learning experts are in growing demand.  In recognition of the increasing need for skilled AI professionals, the YSDA faculty is designing a new one-year machine learning career advancement program for students and professionals that will be offered at the new TAU location.  The new program aims at serving students with diverse academic and professional backgrounds who can apply their machine learning expertise across many industries.

We are excited about the work ahead in 2018 and the opportunity to help educate the next generation of AI experts who will be innovating for years to come.  Last week the Yandex TAU partnership kicked off with a ceremony in which Yandex CEO, Arkady Volozh signed the agreement for the initiative with TAU President Joseph Klafter.  

A Grateful Look Back at 2017

Open letter from Arkady Volozh, CEO of Yandex

2017 was an outstanding year for Yandex. Our team made significant  strides in advancing the ways we help our millions of users more easily and efficiently navigate the online and offline world. In this post, I want to highlight some of our accomplishments over the past year.  I also want to express my gratitude to the truly impressive team that made 2017 such an incredible year for Yandex.

This year, as we celebrated our 20th anniversary, we delivered significant advancements in AI that are a culmination of two decades of work in machine learning.  In 2017 we launched our Machine Intelligence and Research (MIR) division, a new cross-functional unit that has unified our core machine learning technologies. MIR enhanced and launched several intelligent products and services, including the initiative to open-source CatBoost, an award-winning machine learning library that has seen significant adoption with thought leaders in the global AI community.  I want to thank all of our team members who contributed to AI enhancements on products such as our core Search product, Yandex.Zen, Yandex.Weather, Yandex.Music, and Yandex.Translate.

I am proud of all of the talented men and women who work at Yandex and their contributions to the field of machine learning. This year the Yandex School of Data Analysis celebrated its 10th anniversary of educating the next generation of data scientists in Russia through a free Master’s level program taught by top experts in the fields of Computer Science and Data Analysis. 

Our work here at Yandex has led us to many important achievements that not only impact the experiences of our users but also advancements in the global technology community. This year we were excited to introduce our intelligent assistant, Alice, which represents the next generation of search and is the only mass-market assistant in the world able to freely converse with its users. This year we also made strides in advancing the future of ridesharing.  The Yandex.Taxi team launched its driverless technology with the debut and successful testing of its autonomous vehicle.  Autonomous vehicles will transform the economics of the ridesharing ecosystem and we are proud to be leaders in the space.

2017 represents a transformational year of growth for Yandex in the transportation industry.  Our Yandex.Taxi business continues to revolutionize transportation with faster, cleaner and more expansive services for our users in 300+ cities across multiple markets.  Yandex.Taxi has provided over 335 million rides from its launch through the end of September 2017.  In July, we announced a deal valued at $3.4B in which Yandex.Taxi and Uber’s local ridesharing business will be combined in Russia and neighboring states to offer an even better and more efficient services for our users. 

This year we also launched Yandex.Auto, a multifunctional voice-controlled solution for connected car multimedia systems that incorporates Yandex solutions into the dashboards of cars produced by Toyota, Jaguar Land Rover, AvtoVaz, Ford and Kamaz.

As we look ahead to 2018, we are also excited about this year’s joint venture plans with Sberbank to build an end-to-end eCommerce marketplace for Russian online shoppers.  In the coming years, Sberbank’s $500M contribution will enable us to rapidly accelerate the development of our leading eCommerce platform, Yandex.Market, which provides 20 million monthly users with 150 million product offerings from over 20,000 domestic and international merchants.

And as I wrote back in April, users and the technology community have a lot to appreciate in 2017 and to look forward to in the years ahead now that Android offers a truly open platform for all application developers in Russia. For the first time, 55 million Russian Android users were given a choice of search engines on their mobile devices this year.  Moving forward, all new Android smartphones in Russia will prompt consumers to choose which search engine they would like to use on their devices.  This has led to a more dynamic and competitive ecosystem that breeds innovation and opportunities. Innovation of our mobile search offerings and the opening of this ecosystem has led to a 10 percentage point increase in Yandex market share on Android devices in 2017. 

Looking back at these accomplishments, I’m in awe of the year we’ve had and I am humbled by the talent and drive within our organization that has made this progress possible.  This year we have not only improved upon many of our existing services but we have explored new ways we can help our communities through new initiatives like our Yandex.Health telemedicine offerings or our digital learning platform for early education

I want to thank our team for all their hard work this year and our users for choosing Yandex.  I’m eager to build on our momentum in 2018 and continue to innovate and improve the exceptional experiences we offer users at every step of their journeys. By combining technological innovation with best-in-class products and services, there is no limit to what Yandex and its users can achieve in the new year.

Happy New Year!

Arkady

2017 Yandex Top Trending Search Topics in Russia

As the leading search engine in Russia, everyday Yandex provides results to over 250 million user queries. At the end of the year our research team compiles these queries and analyzes them to publish a list of the year’s top search trends.  Usually we don’t publish this in English but since we heard the world was wondering what makes the average Russian laugh, cry, and pay attention, we thought we’d translate their research to English this year.  

While these categories don’t cover everything, it gives us a great picture of what united Yandex users throughout 2017.  Although it’s our job to provide information, we connect with it too.  As our world has become increasingly intertwined through the power of technology, you may find that from your phone or laptop thousands of miles away from Russia, you too searched for similar topics in 2017 and can relate to this list. 

The very top of the first category “Events” starts with one of the more difficult moments of the year that united us - a deadly terror attack in a Saint Petersburg metro station.  Events such as these create concern but ultimately bring us together as a community.  That week people came together such as offering their homes to those in need and at Yandex we were glad to be among those helping by providing free Yandex.Taxi rides.

When it comes to the categories of “Men” and “Women,” Yandex users searched for a number of local and international celebrities, taking interest in their lives, such as the beloved Eurovision star, Dima Bilan and opera singer, Maria Masksakova. As for the  “Things and Phenomena” category, cryptocurrencies, fidget spinners, and the iPhone X proved to be just as popular in Russia as they were elsewhere.  

In the same category, we were pretty humbled to see our intelligent assistant, Alice, make waves with Yandex users after its mid-October launch this year.  Not only has Alice gained popularity for being useful but also for being sassy and entertaining. Thanks to all our users for appreciating our unpredictable robot and sharing your interactions.

It wasn’t a major surprise to see the Ice Hockey World Championship topping the “Sports” category in 2017. Fans searched for information on hockey, football, and the McGregor Mayweather fight among other sporting events. 

For users who weren’t watching sports or were in between sporting events, they were looking up movie times to go see It and Despicable Me 3 among others.  And when at home, of course, our users were watching Game of Thrones and other popular shows.  Before the premier of season seven in July, we actually had the privilege of giving Jon Snow a Yandex.Taxi ride among our millions of other rides in 2017 (passengers don’t usually ride shotgun or carry swords but we made an exception). 

Last but certainly not least, is our category on “Memes,” which these days some would argue includes some of the most valued content on the internet.   Once again, our list of memes proves we can all appreciate a good laugh and there’s always that one viral trend we enjoy.  This year Yandex users appreciated a solid list of memes, including “Zhdun” or “the one who waits” all over the place, including at our office in Moscow. 

Thanks to our users’ queries and also to our new and improved deep neural network based search platform, we continue to provide users with the quality service they have known and loved for two decades.  Thanks to our millions of users for turning to Yandex in 2017 to navigate their daily lives, we look forward to 2018!

For more comprehensive version of this research in Russian, please visit our research page.

Yandex.Health Provides Russian Users With Accessible Medical Advice for the Modern Age

50 million monthly users rely on Yandex services to help them better navigate the online and offline world. We are constantly working to improve our search and other services by listening to our users and responding to their needs. With the input of our users, we discovered an upward trend in health-related search queries, which are the most searched topic on mobile devices today. In response to an increased dependence on online resources for real-time answers relating to health, Yandex recently launched Yandex.Health, a mobile application that allows Russian users to connect to doctors, regardless of location.

The Yandex.Health application enables users to obtain affordable, on-the-go health advice from qualified medical professionals 24 hours a day, seven days a week anywhere an internet connection exists. All Yandex.Health consultants are experienced Moscow-based medical professionals certified by a special Yandex.Health training course. Users can complete their initial medical consultation via videoconference or text for 99 rubles ($1.70), and follow up appointments for 499 rubles ($8.50). 

Yandex.Health currently offers medical advice to Russian-speaking users across Russia, Belarus, Kazakhstan and several countries across Europe. The Yandex.Health app now holds the top ranking in the “Free Medical” app store category after launching earlier this year. It is the most downloaded online consultation service in Russia with thousands of consultations and counting. 

The consultation process is designed to provide patients with easy-to-access medical advice from dedicated professionals. For example, if a user in Moscow has a rash, the process begins with a brief text conversation where the user can describe symptoms and send relevant images to the first available doctor. If the user is unable to use video, the doctor can continue the consultation and learn more about the user’s symptoms via text message. The user will then receive a detailed report with doctor recommendations that can be viewed anytime in the Yandex.Health application.

In addition to consultations, Yandex.Health offers a feature for users to order medication online and pick it up in person. This added service combines Yandex’s data and technology with the resources and experience of pharmacies across Russia with information on roughly 20,000 different types of medicine from over 14,000 participating pharmacies in 78 regions across Russia. 

“Yandex constantly aims to improve the quality of everyday life for users online and offline,” says Grigory Bakunov, Head of Yandex.Health. “Yandex.Health provides our users with more accessible medical advice so people can better monitor and manage their health with the help of qualified healthcare professionals.” 

Yandex.Health changes the way users address their health needs by providing reliable, quick, and convenient online medical advice to users who might otherwise use online searches to diagnose themselves or wait for an appointment with a medical expert.  While Yandex.Health does not replace the need for in-person medical care, the application empowers patients with a reliable resource to virtually manage their health. As users become ever more dependent on their mobile devices, we are excited that Russian users now can now easily connect with doctors and take care of their health from home or on the go.

Yandex.Health is available as a desktop service and for iOS and Android for Russian-speaking users in Russia, Belarus, Kazakhstan and some countries in Europe. For more information on Yandex.Health and its availability, visit https://health.yandex.ru/.

Winter Is Coming: Yandex.Weather Nowcasting Helps Users Plan for Precipitation

Like the Seven Kingdoms of Westeros, Russia is known for its vast size and wide range of weather. In particular, many people associate Russia with its distinctive harsh winters that last about five months of the year. The coldest stretch of the Russian winter begins in November and extends through March. During these months, temperatures can regularly reach as low as –34°C (–30°F) in Siberia, one of the coldest regions of Russia that also experiences over 1,000 mm of precipitation in some areas. 

With December fast approaching, weather is shifting and Game of Thrones fans know that “Winter is coming.” To better manage the weather in Russia, over 35 million monthly active users rely on Yandex.Weather, Yandex’s hyperlocal, real-time weather forecasting application, for up-to-the-minute weather updates.

Yandex.Weather incorporates machine learning to provide users with a world best precipitation forecast system. Our weather forecasting technology, Yandex.Meteum, produces 43 percent greater accuracy in predicting precipitation and 25 percent more accurate temperature forecasts than competing weather forecasting services.

While traditional weather forecasting models rely on a combination of data models and surface weather observations to predict weather, Yandex.Weather adds deep learning to the equation. When traditional models are incorrect, for example overestimating rainfall during a cyclone, the temperature is corrected manually with surface observations. Yandex.Weather’s technology, on the other hand, replaces the need for surface observations with the use of deep learning. 

Within the last year, we enhanced our precipitation forecasting technology by incorporating nowcasting.  Yandex nowcasting uses radar imagery to forecast changes in weather using a deep learning neural network to handle transformations, transitions and other changes with the latest radar shot. This technology enables forecasting to be done on a minute-to-minute basis with best-in-class accuracy.   Now users can get push notifications that let them know the moment snow is about to stop in their exact location

Highly accurate, near real-time weather forecasting is clearly useful for people experiencing the variety of weather across Russia. But even within individual cities there is still considerable differences in weather that impacts users’ daily plans. Where traditional weather services generalize results by city, Yandex.Weather shows users hyperlocal results down to the city block.

With hyperlocal forecasting, Yandex.Weather users in one neighborhood may use the application to track a brief sleet storm on the weather map, while users just a few blocks away can receive forecasts showing clear skies in their location. 

Below shows such a scenario that played out yesterday near the Chernyshevskaya metro stop in St. Petersburg, where a user viewing our weather map could have used our service and decided to step inside a coffee shop for some tea during the passing sleet. 

Meanwhile, a user closeby at the Nevskiy Prospect metro using Yandex.Weather might have seen that conditions were fair and recognized they had a half hour to run nearby errands before the sleet reached them. 

As users adjust to shifting weather, their plans impact the demand for nearby businesses including our ridesharing service, Yandex.Taxi. Together, the coming stormfront and surging demand for Yandex.Taxi rides show how much the weather and Yandex nowcasting technology can impact users and businesses.  

With the recent introduction of nowcasting, we can now provide communities with an even more advanced machine learning based forecasting tool to help them more easily navigate their days and stay warm during the “Long Night” of winter!

Celebrating 10 Years of the Yandex School of Data Analysis

Over the years Yandex has launched several education initiatives ranging from learning platforms to high school and master’s level courses. 2017 marks the 10-year anniversary of one of our most impactful educational initiatives, the Yandex School of Data Analysis (YSDA), a free Master's-level program in Computer Science and Data Analysis. In Russia, Yandex is privileged to have access to some of the most talented math and science minds in the world but 10 years ago, Yandex co-founders Arkady Volozh and Ilya Segalovich realized there was a real need to foster these talents and offer students a program for advanced data science.  

 “Together with well-known pattern recognition specialist, Ilya Muchnik, our co-founders considered the need beyond programmers, to programmers with advanced knowledge of the most modern machine learning practices. There was a serious demand for people to lead Yandex and the entire industry down a new path,” says Yandex Director of Human Resources and Director of Computer Science Department at YSDA, Lena Bunina. “And it was clear that we needed to undertake this ourselves.”

Since 2007, the YSDA has been offering Russian students two vigorous years of training from top experts in the most advanced data science topics. Students leave with a profound understanding of theoretical foundations and hands-on experience in applications such as computer vision and  machine translation. “At YSDA, we focus less on theories and more on developing well-rounded students,” says Bunina. “It’s important for students to work in labs, solve problems and receive practical experience.” YSDA students have a unique opportunity to put their data processing and research skills to use as part of YSDA’s collaboration with the LHCb experiment at CERN, the European Organization for Nuclear Research.

YSDA students also have internship opportunities at Yandex that allow them to further expand their training. Interns have the opportunity to work side-by-side with Yandex data scientists helping to deliver our users exceptional customer experiences.

Initially, the school started in Moscow instructing a class of 80 students in the department of Data Analysis. Our academic reputation, coupled with the growing demand for data scientists in today’s AI-centric world,, have created a huge demand for YSDA courses. Last year we received over 4,000 applications from top universities, welcoming 211 students who passed our rigorous entrance exams.

Today, the program has campus branches in Moscow, Yekaterinburg, Novosibirsk and Minsk, plus online offerings in both English and Russian on Coursera and partnerships with some of Russia's leading research institutions and universities.  The Yandex School of Data Analysis offers the Department of Data Analysis and the Department of Computer Science, and with a specialization in Big Data.

At the YSDA, it’s our mission to prepare students to succeed far beyond the walls of our classrooms. “YSDA’s unique blend of science and practice prepares graduates for a wide range of professional options in science, research, product development, analytics and more,” says Misha Levin, Chief Data Scientist at Yandex.Market and YSDA lecturer.

In 2009, we graduated our first 36 students and this past year proudly graduated 123 students.  After ten years, over 600 YSDA graduates are changing the way technology impacts our lives. One of them is Ruslan Mavlyutov, a 2011 YSDA graduate who now works as a Machine Learning Engineer at Apple. “YSDA elevated my machine learning career and I feel privileged to have had the opportunity to study there,” says Mavlyutov. “My peers and I had the unique opportunity to be early ML ‘adopters’ at YSDA enabling us to start and lead ML endeavours at Yandex and other tech giants like Google, Facebook, Microsoft and Apple.” 

“YSDA has created a network of bright minds that pumps ideas across countries, industries and companies. In almost every well-known IT company I can find someone who has studied at the YSDA." Mavlyutov adds, "Those are the people whom you can trust and rely on their expertise.”

We’re excited to be at the forefront educating the next generation of data scientists over the next 10 years. Thank you to all of past and present students and instructors of the Yandex School of Data Analysis! 

Say “Privet” to Alice, Yandex’s Intelligent Assistant

Today we are excited to officially introduce the world to a new AI assistant, Alice. Alice speaks excellent Russian and integrates multiple services in one centralized tool.  Built to authentically interact with people as they go about their day, Alice understands users’ natural language requests and provides contextually relevant answers. 

Alice helps users to easily and efficiently navigate their lives in a variety of ways by planning routes to destinations, providing weather forecasts, and sharing the latest news, among a number of other useful tasks. In addition to providing users with a wealth of online information through Yandex search, Alice integrates our services such as Weather, News, Maps, Transport, and Music, offering a centralized and fluid experience to assist users with their day.  For instance, to find a restaurant nearby, one can simply ask for “a dinner place nearby” - and to get directions to the suggested restaurant, they can add, “how do I walk over there?”

In developing Alice, we utilized our knowledge of the more than 50 million monthly users who interact with Yandex services.  Coupling our machine learning capabilities and 20 years of experience with Russian users and Russian language, we started experimenting with a personal assistant to specifically serve the needs of Russian users. We released a beta version of Alice in May 2017 to further test our ideas and understand how users could benefit from using Alicе.  Recently, we added a neural network based “chit-chat” engine to Alice that allows users to have free-flowing conversations about anything. It is a unique feature that our users find surprisingly delightful and different from other major voice assistants.  

Using web-scale datasets and deep neural networks, we trained Alice to listen, understand, and speak to users using natural language.  As a result, it provides an authentic and human-like personal assistant experience.  For instance, when a user asks Alice, “What’s the weather in Moscow?” and then follows with a question in slang asking, “And what about Peter?” Alice understands the intent and provides the weather forecast for St. Petersburg. 

Alice leverages speech recognition and synthesis capabilities of SpeechKit, Yandex’s world-class toolkit that is used across many of our products, from Navigator to Music. Speech recognition is especially challenging for the Russian language due to its grammatical and morphological complexities.   According to word error rate (WER) measurements, SpeechKit provides world-best accuracy for spoken Russian recognition, enabling Alice to understand speech with a near human-level accuracy.  

SpeechKit’s text-to-speech (TTS) technologies utilize multiple machine learning methods, such as neural networks and gradient boosting, to synthesize responses that sound natural and authentic. In addition to authentic responses, users who are fans of Spike Jonze’ film Her will recognize that Alice’s voice is derived from Tatyana Shitova, the recording actress who dubbed the voice of Samantha in the Russian language version. 

Smartphone users can now use Alice in the Yandex search application for iOS and Android and in a beta version of Yandex Assistant for Windows.  Alice will also soon be integrated into Yandex.Browser, followed by other Yandex products. Thanks to users for choosing our intelligent assistant, and even helping us name it.   Welcome to the world, Alice – we look forward to talking to you!