Name: How Google Translate Uses Math to Understand 134 Languages
Uploaded: 2024-05-26T04:01:00Z
Duration: 8 min 20 s
Description: Google Translate's live text translation uses your phone camera to instantly interpret your surroundings in up to 134 languages. We dig into the technology, and why it can still botch translations. Photo illustration: Michael Tabb

https://www.barrons.com/client

Topics

Memberships

Tools

Customer Service

Network

Newsstand

For Business

For Education

For Advertisers

Account

About Barron's

bolded

unBolded

That's according to Okta CEO Todd McKinnon, who also spoke about how the company's name is tied to pilots and why flexibility is a core aspect of Okta's business.

https://m.wsj.net/video/20250710/d3fadd54-0fc6-4961-a2c0-0d858131e3c7/1/hls/manifest-hd-wifi.m3u8

Why Okta Wants 'Authentication to Disappear'

Dr. Robert Grossman, CEO of NYU Langone Health, which has consistently ranked as one of the best hospitals in the nation. talked about the Trump administration's plans to significantly cut the budget of the National Institutes of Health (NIH).

https://m.wsj.net/video/20250715/02e28b09-0b7e-4a48-8227-6dbbb42d9598/1/hls/manifest-hd-wifi.m3u8

NYU Langone CEO on NIH Cuts: 'That Takes a Scalpel, Not a Sledgehammer'

Though quality of care is excellent in the U.S., access to care needs to be improved, said Dr. Robert Grossman, CEO of NYU Langone Health, which has consistently ranked as one of the best hospitals in the nation.

https://m.wsj.net/video/20250715/fc3563ea-508b-4d6d-b32a-a77f939c6e5b/1/hls/manifest-hd-wifi.m3u8

NYU Langone CEO Says This Can Help the U.S. Government Fix Healthcare

Dr. Robert Grossman, CEO of NYU Langone Health, spoke to At Barron's about how the health system has transformed and changes he made along the way.

https://m.wsj.net/video/20250703/c25a5233-a5a6-48c9-bf10-ea3948ab7d7b/1/hls/manifest-hd-wifi.m3u8

How This Massive NYC Health System Changed Its Business Model

"The economic implications for the U.S. are profound," said Greg Case, CEO of Aon.

https://m.wsj.net/video/20250709/57231b7d-6d25-4c2e-ae5c-f0b6a6299196/1/hls/manifest-hd-wifi.m3u8

Why Aon's CEO Is Betting on GLP-1 and Other Weight-Loss Meds

"It creates opportunity, which is terrific, but it also creates volatility," said Greg Case, CEO of Aon, talking about the connectivity and complexity underpinning today's business environment.

https://m.wsj.net/video/20250709/c5c85274-4515-484f-8cf4-2a6b3056b927/1/hls/manifest-hd-wifi.m3u8

Why Aon's CEO Thinks Volatility Isn't Going Anywhere

Greg Case, CEO of Aon, explains 4 causes of global volatility the risk manager helps clients navigate.

https://m.wsj.net/video/20250626/65d52c3a-2940-4439-acfa-78e7f53dde15/1/hls/manifest-hd-wifi.m3u8

4 Megatrends That Cause Volatility in the World: Aon CEO

Scott Bok, the former board chair of the University of Pennsylvania, breaks down the financial risks and implications that come with removing tax-exempt status from colleges and universities.

https://m.wsj.net/video/20250709/c8469d5c-8f50-48fd-acb8-97f3b510ea21/1/hls/manifest-hd-wifi.m3u8

Taking Away Tax-Exempt Status: A “Nuclear Weapon Against Universities”

Scott Bok, the former CEO of Greenhill and the former board chair of the University of Pennsylvania, discusses navigating private markets and a "rapidly evolving" Wall Street.

https://m.wsj.net/video/20250709/9078df41-7fd7-4d1e-9c18-380e4f2b0868/1/hls/manifest-hd-wifi.m3u8

How Regulatory Concerns Impact Private Markets

At Barron's

Saira Malik, chief investment officer of Nuveen, makes the case for more gains in 2023.

https://m.wsj.net/video/20230925/4d8aa5ee-77aa-4400-884b-1fafeff893ec/1/hls/manifest-hd-wifi.m3u8

S&P 4700?

David Bailin, chief investment officer of Citi Global Wealth, offers his take on the latest IPO activity and what it says about the strength of capital markets.

https://m.wsj.net/video/20230925/5f4d4a28-d83a-40e3-ad94-28bc25b1c3bc/1/hls/manifest-hd-wifi.m3u8

IPOs: Making a Comeback

Chris Harvey, head of equity strategy at Wells Fargo Securities, explains what would make him more bullish on stocks and when he sees a Fed rate cut coming.

https://m.wsj.net/video/20230918/1f534ddf-5da9-4d1d-9926-fda63e90468e/1/hls/manifest-hd-wifi.m3u8

Cuts on the Horizon?

Tom Kennedy, chief investment strategist for J.P. Morgan Global Wealth Management, explains why he thinks concerns around a slowdown in China are overblown.

https://m.wsj.net/video/20230918/09304272-5f0c-49df-892a-3a3d4622c9c3/1/hls/manifest-hd-wifi.m3u8

Evaluating China Risk

Liz Young, head of investment strategy at SoFi, discusses how market moving the August inflation data could be.

https://m.wsj.net/video/20230911/50b8c6b4-8fd3-4d6f-adff-dd0a024a57d7/1/hls/manifest-hd-wifi.m3u8

Inflation in the Spotlight

Lindsey Piegza, chief economist at Stifel, offers her take on the biggest risks to the economy right now.

https://m.wsj.net/video/20230911/cac885e4-b322-40f8-876c-ebd443fe9d29/1/hls/manifest-hd-wifi.m3u8

Assessing Economic Headwinds 

Dan Ives, managing director and senior equity analyst at Wedbush Securities, explains why he thinks Apple will continue to be a market leader.

https://m.wsj.net/video/20230905/1a48f030-5a5a-401c-a571-ec9115a0155e/1/hls/manifest-hd-wifi.m3u8

Prove-me Moment

Ross Mayfield, investment strategy analyst at Baird, highlights bullish catalysts that could drive the market higher between now and year-end.

https://m.wsj.net/video/20230905/729974df-4594-4fc6-a385-5457b1d87e32/1/hls/manifest-hd-wifi.m3u8

Gearing up for a Rally

Matthew Luzzetti, chief U.S. economist at Deutsche Bank, discusses what’s next for the Federal Reserve and the economy.

https://m.wsj.net/video/20230501/7264fcc9-eea9-4d99-b839-4cd4c20500c9/1/hls/manifest-hd-wifi.m3u8

Recession Ahead 

MarketBrief | Clips

MarketBrief Clips

David Bailin of Citi Global Wealth and Saira Malik of Nuveen debate the probability of a recession and discuss where they’re finding opportunities in equities and fixed income.

https://m.wsj.net/video/20230925/a61dd831-40b8-4727-934f-077d2b880711/1/hls/manifest-hd-wifi.m3u8

Investing in a Slowing Economy 

Take stock of your investments in less than 10 minutes with new show from Barron’s and MarketWatch.

Chris Harvey of Wells Fargo Securities explains why he believes the Federal Reserve is done hiking interest rates while J.P. Morgan Global Wealth Management’s Tom Kennedy makes the case for multi-asset investing.

https://m.wsj.net/video/20230918/84e9a4a4-4e50-4b7b-934c-9a532f9803fc/1/hls/manifest-hd-wifi.m3u8

Rate Hikes in the Rearview?

Lindsey Piegza of Stifel discusses the upside risks for inflation while SoFi’s Liz Young explains why she’s cautious on the market through year-end.

https://m.wsj.net/video/20230911/395ecb74-e349-45b0-a6b8-f91b8874aaf8/1/hls/manifest-hd-wifi.m3u8

Pricing Pressure & Frothy Valuations

Baird’s Ross Mayfield makes the case for a better than expected September for stocks while Dan Ives of Wedbush Securities explains why big tech can rally another 15%.

https://m.wsj.net/video/20230905/156bf778-e13d-41ef-b750-55e2ef1c0162/1/hls/manifest-hd-wifi.m3u8

September to Remember? 

Kristen Bitterly of Citi Global Wealth Management explains why the strong start to the year is nothing more than a bear market rally while Eric Winograd of AllianceBernstein offers his outlook for the Fed, inflation, and the labor market.

https://m.wsj.net/video/20230220/ae07e591-f017-4e82-babb-c80144e7d42f/1/hls/manifest-hd-wifi.m3u8

Time to be Skeptical?

Anastasia Amoroso of iCapital explains why she thinks the stock market rally is nearing a ceiling while U.S. Bank Wealth Management’s Lisa Erickson discusses where she’s finding investment opportunities in an uncertain environment.

https://m.wsj.net/video/20230213/61be15a3-f5ac-4a25-b944-edd15e605e30/1/hls/manifest-hd-wifi.m3u8

Hitting a Wall

Jack Manley of J.P. Morgan Asset Management explains why now is the time to leg back into risk assets while BlackRock’s Rick Rieder offers his top fixed income opportunities.

https://m.wsj.net/video/20230206/0be0daa9-d29a-4350-b277-a9ee6ed9a2ea/1/hls/manifest-hd-wifi.m3u8

Two Ways to Play

Amid impressive January gains, Cameron Dawson of New Edge Wealth discusses how she’s positioning her portfolio and Mark Zandi of Moody's Analytics explains why he thinks the economy can still avoid a recession.

https://m.wsj.net/video/20230130/a8c37d62-592b-4830-9466-65c3824205fe/1/hls/manifest-hd-wifi.m3u8

Gauging Upside Potential

Mike Schumacher of Wells Fargo Securities explains why he’s nervous about stagflation while Sylvia Jablonski of Defiance Investments offers her top portfolio picks.

https://m.wsj.net/video/20230123/1e752a76-b7d4-4802-821a-837d6176f979/1/hls/manifest-hd-wifi.m3u8

Wall Street’s Biggest Risk

MarketBrief | Full Episodes

MarketBrief Full Episodes

After 10 straight hikes, the central bank switched gears and opted to keep rates steady. But that doesn't mean the Fed's inflation fight is over.

https://m.wsj.net/video/20230616/9dce6e5c-4c62-4aa6-b432-d3407ac41aea/1/hls/manifest-hd-wifi.m3u8

The Fed's Rate Pause, Explained

A publicly traded company can increase it's number of shares available by splitting its stock. Here's why companies may do it and how it affects investors.

https://m.wsj.net/video/20221115/f37dedad-4403-4f6d-bd22-067d0fb148df/1/hls/manifest-hd-wifi.m3u8

Stock Splits Are Big This Year. Here's What They Mean for Investors.

Here's why a publicly traded company may decide to go private and what it means for its shareholders.

https://m.wsj.net/video/20221025/9fb3fa20-e2ac-485b-aa4d-8fcf3ebd3151/1/hls/manifest-hd-wifi.m3u8

What Happens When a Stock Goes Private?

What Happens When a Public Company Goes Private?

When saving for retirement, there are many different accounts and tax strategies to consider. Here's how to tell if a Roth IRA conversion could be right for you.

https://m.wsj.net/video/20221021/624f992c-db58-4144-93cc-b888c6948059/1/hls/manifest-hd-wifi.m3u8

What to Know About Roth IRA Conversions

As recession fears loom, here are three ways investors can prepare and protect their portfolios.

https://m.wsj.net/video/20221020/5d94fa79-7b6d-4c51-8ac7-8c523c99d487/1/hls/manifest-hd-wifi.m3u8

Preparing Your Portfolio for a Recession

Retiring abroad could lower your cost of living, so you can make your savings go further in your golden years. But a permanent move to a new country could be more complicated than you think. Here's what you should know.

https://m.wsj.net/video/20220823/7a028383-44a0-4957-a070-0018f046ec97/1/hls/manifest-hd-wifi.m3u8

Thinking Of Retiring Abroad? Here's What to Consider.

Billionaire-backed space companies have made space tourism a reality. How to participate in a potential private-sector space boom.

https://m.wsj.net/video/20220818/99bac587-9be5-48e6-9376-48f3bb8d55cf/1/hls/manifest-hd-wifi.m3u8

How To Invest In Space Tourism

When you hear the words 'electric vehicle', you might immediately think 'Tesla'. But as more automakers enter the EV competition, Tesla might have trouble holding its lead. Here's what investors need to know.

https://m.wsj.net/video/20220722/111776c7-d9d2-4cd2-8194-4c58b0cb7e57/1/hls/manifest-hd-wifi.m3u8

Is Tesla Miles Ahead of Others in the Electric Vehicle Race?

Chinese tech company DiDi Global, which runs a ride-sharing app, has announced it plans to delist from the New York Stock Exchange. Investors are watching and waiting to see what other Chinese giants with U.S. listings, like Alibaba and JD.com, will do. Here's what delisting entails.

https://m.wsj.net/video/20220722/eacf026e-7303-4eb7-80ab-3e2344e2b120/1/hls/manifest-hd-wifi.m3u8

What Happens When a Stock Delists?

Barron's Explains

CEO Cristiano Amon has a plan to shrink Qualcomm’s reliance on phones and grow its role in AI, cars, and beyond. Investors are skeptical—should they be?

https://m.wsj.net/video/20241127/99579ccd-a5c1-4acc-ac31-32469f7d8b1c/1/hls/manifest-hd-wifi.m3u8

What's Next for Qualcomm?

On the Barron's Streetwise Podcast, Barron’s senior writer Al Root sits down with Jack Hough to discuss Toyota’s recent success with hybrids, the coolest cars at the New York Auto Show, and what’s ahead for Tesla stock.

https://m.wsj.net/video/20240329/f163bbd7-0cb6-4c6f-b7f9-a85ae5cd2553/1/hls/manifest-hd-wifi.m3u8

Is Electric Vehicle Demand Cooling Off? 

On the Barron’s Streetwise podcast, Rystad Energy’s Alexandre Ramos Peon discusses how U.S. oil producers have boosted profitability and production despite fewer wells.

https://m.wsj.net/video/20240326/0a4b30c7-379c-460f-abc3-838a7f1eb1a9/1/hls/manifest-hd-wifi.m3u8

The Outlook for Oil

On the Barron’s Streetwise Podcast, Jack Hough pushes back against one of Bitcoin’s most popular valuation models.

https://m.wsj.net/video/20240318/b38cc34a-5064-4a6a-a47c-4c855de11973/1/hls/manifest-hd-wifi.m3u8

Bitcoin as 'Digital Gold' 

On the Barron’s Streetwise podcast, Raphael Zagury of Swan Bitcoin shares his bitcoin price model with Associate Editor Jack Hough.

https://m.wsj.net/video/20240312/c0acb0bf-e4e3-46ca-8fd5-13af6fa401e5/1/hls/manifest-hd-wifi.m3u8

The $600,000 Case for Bitcoin

Kathy Jones, Chief Fixed Income Strategist at Schwab, says it might not matter. Plus, the outlook for yields and the national debt.

https://m.wsj.net/video/20240305/0505813c-e38b-47cb-ade2-e7c3aff68dbd/1/hls/manifest-hd-wifi.m3u8

Bond Funds or Individual Bonds?

Brian Niccol on developing new customer favorites, taking menu tips from TikTok, and the outlook for growing the business.

https://m.wsj.net/video/20230725/dec91556-4dbe-49e6-85d9-ed0e8233ac02/1/hls/manifest-hd-wifi.m3u8

Chipotle's CEO on How He Plans to Double the Business. Again.

Jim Farley on competing with Tesla, and why Ford is favoring Level 3 autonomy over full self-driving capability.

https://m.wsj.net/video/20230519/9aa4288a-39a1-4fb8-8b9d-3be0c58adc18/1/hls/manifest-hd-wifi.m3u8

Ford CEO On the Outlook for EVs and Robo Cars

J.P. Morgan Asset Management's David Kelly says inflation is like a rollercoaster: It will come down again.

https://m.wsj.net/video/20230505/5d8d3d70-598d-4ee4-a76e-21381c911e40/1/hls/manifest-hd-wifi.m3u8

Inflation, Attractive Bonds, and Value Abroad

Barron's Streetwise

Stocks are expensive, risks abound, and AI is about to change the world. Other than that, building a calamity-proof retirement portfolio should be a cinch. Tune in as two veteran money managers size up the markets and share their investment ideas.

https://m.wsj.net/video/20250211/17a5e7d6-7c36-44b0-a35e-bf5ac3a24194/1/hls/manifest-hd-wifi.m3u8

Saving for a Sunny Day

Research shows that people greatly underestimate the healthcare costs they’ll face in retirement. Learn from experts how to estimate those costs, prepare for potential long-term care needs, and manage healthcare expenses in retirement.

https://m.wsj.net/video/20250211/e7c022d9-badf-4e95-8e7c-0b6fce9f7823/1/hls/manifest-hd-wifi.m3u8

Are You Fiscally Fit?

Surging power demand, new energy sources, and growing competition have spurred the utility industry to become more innovative than ever before. Our panelists will unpack the changes afoot and explore what lies ahead for companies, customers, and investors.

https://m.wsj.net/video/20240917/001ea098-1fcc-4da5-9f0e-a3b149bbb2fb/1/hls/manifest-hd-wifi.m3u8

Not Your Father's Utility

Modernizing America's grid will take creativity and money -- lots of money. Learn how players across the power sector can achieve their electrification goals and serve new customers without breaking the bank for consumers.

https://m.wsj.net/video/20240917/bd6bd43a-bb07-4b7f-9d1c-6ae04220bea9/1/hls/manifest-hd-wifi.m3u8

Ready for a Revamp?

The launch this year of Bitcoin ETFs has made it easier for investors to buy and trade the cryptocurrency. But is that a wise move, and if so, how much crypto should you own?

https://m.wsj.net/video/20240529/cbb77f15-ef70-445d-85ae-5f02c24ea1ef/1/hls/manifest-hd-wifi.m3u8

Investing in Cryptocurrencies

Bitcoin and other digital currencies reside on software networks that aim to revolutionize everything from finance to art. Barron's talks to industry experts about the outlook for blockchain technology and its potential uses.

https://m.wsj.net/video/20240529/8f60a5ea-6de4-4c3c-b7c2-12b11aaa99f3/1/hls/manifest-hd-wifi.m3u8

Is Crypto Really a Game-Changer?

Persistent inflation means retirement savings don't go as far as they once did. We discuss the best inflation hedges, and how retirees can benefit from higher-for-longer interest rates.

https://m.wsj.net/video/20240429/69577ad6-cbaf-4d34-96f1-c42136e26aa2/1/hls/manifest-hd-wifi.m3u8

Protecting Your Nest Egg from Rising Prices

The impact of inflation is felt unevenly across the economy and markets. Learn which industries, and companies do best in a “sticky” inflation era, and how fixed income, alternative assets, and gold can help investors hedge against further price growth.

https://m.wsj.net/video/20240429/bfee3cb8-715f-4323-929f-43a73fd58877/1/hls/manifest-hd-wifi.m3u8

Don’t Trim Your Inflation Hedges

Science, tech, and better healthcare delivery are helping people live longer and improving quality of life. Two healthcare investment experts tell us about some of the most promising developments in medicine, and the companies behind them.

https://m.wsj.net/video/20240305/33bed2b1-bdef-401f-bb72-18f7a43f2548/1/hls/manifest-hd-wifi.m3u8

Longevity: An Investor's Playbook

Barron's Roundtable

Barron's Advisor The Way Forward

Investing in Tech

Barron's Investing in Tech Clips

A Better Economy & Wealth Gap Events

Wealth Gap

Level Up

Barron's Events

Back to Business

Great Investors

MarketWatch

Video Center - Barron's home

Google Translate's live text translation uses your phone camera to instantly interpret your surroundings in up to 134 languages. We dig into the technology, and why it can still botch translations. Photo illustration: Michael Tabb

https://m.wsj.net/video/20240524/5e6035bc-36e2-4681-b71a-2e549b634665/1/hls/manifest-hd-wifi.m3u8

How Google Translate Uses Math to Understand 134 Languages

Narrator: In a fraction of a second, Google Translate can make sense of your surroundings. But this isn't the same Google Translate from the early 2000s. Over the past two decades, the technology has gone through a complete overhaul, shifting from a basic pattern matching tool to a sophisticated neural network that handles more than 130 languages. It works by turning language into something computers can understand, math.

Exciting times for people who like language and math.

Narrator: This is the tech behind Google Translate.

There's very little code left today from the early days of the phrase based translation. We have shut down and deleted almost all of it.

Narrator: That Google Translate from two decades ago laid the foundation for what we use today. When it launched in 2006, it worked by playing a matching game. First, the model looked at lots of examples of professional translations scraped from the internet. Then when users entered sentences for translation, the tool would break them into the longest possible chunks of words it had seen before and combine the chunks. It now uses a much more sophisticated machine learning approach. A so-called transformer model, which is the building block of all modern AI. transformers turn language into math by assigning numbers to words.

The key insight is that a series of numbers can represent a meaning. You can then do math with those vectors that shows something about the relationships of the meanings of words to each other.

For each language Google Translate supports, every word gets converted into a vector, which is written like a list of numbers. This way the computer can do math with them. For instance, king minus man plus woman equals queen. The specific numbers assigned to each word don't really matter, and they're different in different languages. But what matters is how each word relates to every other word. It's all based on machine learning from billions of examples. But most of the time you wanna translate something, it's not just an individual word. So the computer also has to figure out how words work together, and this is where transformers, a breakthrough in machine learning come in.

The next generation of neural translation is called the transformer architecture, and this added a level, so it moved from representing the meaning of one word by a row of numbers to putting all the meanings of all the words into a table and doing math on that whole table. And that enables you to do math that talks about not only the meaning of each word, but the importance of the relationships of the words to each other.

Say you're trying to translate this Italian sign into English. First, Google Translate would turn each word into a vector, and those vectors would be put into one giant table or matrix. Then the computer tries to figure out how each word interacts with every other word on this sign. Mathematically, this is basically a lot of multiplication.

The most important kind of magical step is laying them out in a matrix and doing what's called matrix multiplication. And if you do enough of that, you can solve this problem.

All this creates a new list of numbers. This is what's called a context vector, and it's something pretty special. This list of numbers actually represents what the sentence means, not just the sum of all of its words, at least if the model has done its job correctly.

If you put that together and are very clever, which the people who invented transformers were, and you train on a lot of data, which we do, you can eventually get to a collection of numbers that meaningfully represents the meaning of the sentence. So that's called the encoder stage. Then you have a decoder, which roughly speaking is the encoder in reverse.

Narrator: The computer has to decode this back to human language.

The decoder now also goes through lots and lots of operations, and finally you start getting vectors out, which can be mapped back to individual words. So we hopefully get closed for then holiday. So this is how language becomes math.

Narrator: Getting this math to work requires a lot of training. Lots of the numbers in this math problem are chosen randomly and then refined as the computer learns from billions of examples. Before deploying an update with a set of values and weights, engineers run numerous tests with their AI evaluator and then professional human translators who check accuracy. But since every possible combination of words leads to a unique equation, it's impossible to test everything. Since the model has trained on translations going to or from English, it often requires more steps to go between two non-English languages. For example, if you wanna translate something in Japanese to Zulu, it will go from Japanese to English and then English to Zulu.

The first thing that happens when you use Google AR translate is that we have to actually extract the text from the image, and so as you can see here, it detects that now this is Chinese and it translates to English. It makes information a lot more accessible because for many people, typing script in a foreign language is not an option.

The key component is a technology called Optical Character Recognition, or OCR. Google has been using that since 2002 when it started digitizing libraries for Google Books.

Initially, it would do something very simple like pattern matching. So you can think of it as, is this the same as this? Yes, so it's an A or B or whatnot.

Narrator: But now optical character recognition also uses transformers. First, Google Lens identifies lines of text and text direction. Then it determines specific characters and words. Instead of dividing the sentence into words and assigning numbers to each word, though, it divides an image into patches of pixels. These are called tokens.

The encoder of the transformer is going to process all of these tokens simultaneously to predict the best character and the best word eventually.

Narrator: This means the Google Lens, the company's visual search tool can often read things even when it can't make out every single letter.

With transformers, they're able to pick up on grammar. If there is a spelling mistake, the transformer will also be able to use the context to disambiguate and still extract the right word.

After it completes optical character recognition, Google Lens analyzes the layout of all the text. That's how a computer would know to translate this sign as you matter, don't give up rather than you don't matter, give up.

When you look at the newspaper, humans are excellent at just glancing at it and understanding what is the reading order? What should you read first? This is a concept that isn't actually easy to solve technically, it's very hard.

Narrator: The key is for optical character recognition to understand something about the meaning of what it's reading. This is also done through extensive training. After the chunks of text are sent to the translator, Google Lens uses painting models to erase the text off different signs or backgrounds. That way translated text can be placed on top of clean surfaces.

Using generative models, it tries to predict and create pixels that match the surrounding pixels so that when we overlay the translated text, it looks very natural and seamless.

Narrator: This doesn't always work seamlessly.

You know, this one is not picking up the first line. I'm not sure why.

Narrator: Some translations don't fully account for context, which is why alto on this Mexican stop sign might be mistranslated to high. And while optical character recognition can frequently identify text in bad lighting or with complicated perspective, it has its limits.

One of them is with deformable objects. Whenever there is text on like a sweater or cookie wrapper, depending on the pose and the angle, it might be more challenging and difficult to extract the right OCR.

Well-formed grammatically correct, fluent text we're quite good at. Where we have challenges is people using slang, using casual speech in chat and social media. We don't necessarily see as much of that because we don't have access to as much data.

Google is working to add some more features, like letting users refine their translations if they want to. Similar to how you can ask Google Gemini or ChatGPT to make translation more or less formal, or in Chilean Spanish rather than European Spanish. And it's also working to add more languages.

There are an estimated 6,000 to 7,000 languages in the world. Our goal is to support all of them.

The Tech Behind delves into the complex engineering, computing, science, and algorithms that power our favorite technology.

How Google Translate Uses Math to Understand 134 Languages

The Tech Behind

Up Next

At Barron's

View All

MarketBrief Clips

View All

MarketBrief Full Episodes

View All

Barron's Explains

View All

Barron's Streetwise

View All

Barron's Roundtable

View All

Barron's Investing in Tech Clips

View All

Wealth Gap

View All

Level Up

View All

Barron's Events

View All

Back to Business

View All

Great Investors

View All

MarketWatch

View All