How Google Translate Works, and Why It Doesn’t Measure Up

Posted on 02. Sep, 2015 by in Language Learning

With over 200 million daily translations, there’s no denying that Google Translate is a wildly popular translation service. Indeed, machine translation has come very far since its infancy in the early 2000s. Instead of translating words at face value, machine translators have developed complex algorithms to deliver more accurate translations, and some even take into account colloquial language and idioms. Still, the very nature of machine translators prevents them from ever doing a human’s job. Let’s take a look at how machine translators (such as Google Translate) work, what their limitations are, and why they can’t replace the quintessential human touch.

There are a lot of things that this computer can do, though producing an accurate translation is not one of them. Image via Pexels

There are a lot of things that this computer can do, though producing an accurate translation is not one of them. Image via Pexels

How machine translation works

Google Translate, as well as other machine translators, operate on statistics rather than rules. That is, they look for patterns in hundreds of millions of documents that have already been translated by human translators. Google Translate makes special use of UN documents, which are translated in all six official UN languages, and thus provide ample linguistic data. This way, they can weigh a plethora of options for phrases presented by various different (human) translations, and select an educated guess based on the one that occurs most frequently. For example, they detect that, in Spanish, the phrase “darse cuenta” is usually translated as “realize” in English. Therefore, based on statistics, Google Translate will correctly translate the phrase as “realize”, rather than a word-for-word translation, which would appear more like “give account”.

Finding linguistic data large enough to create legitimate statistical analyses is no easy feat. Given that more documents are available in English than in any other language, the data almost always uses English as an intermediary step when translating between two languages that aren’t English. For example, when translating from Russian to Spanish, Google Translate will first translate the text from Russian to English, and then from English into Spanish. As a result, when translating in languages other than English, machine translations actually involve two iterations.

In fact, some language pairs involve even more iterations. If you want to translate some text from, say, Catalan to Japanese, Google will translate it first into Spanish, as most existing Catalan translations are in Spanish. Then, this translated Spanish-language version of the original Catalan text will be translated into English. And finally, the English version of the Spanish version of the Catalan text will finally make it to Japanese — and if you’re lucky, it will still bear some resemblance to the original meaning.

Why it doesn’t make the cut

Google Translate does a good job with very basic translations — especially those whose target language is English — and now even offers alternative interpretations for certain words and phrases. However, the very methodology upon which Google Translate is based prevents it from ever competing with human translators. Here’s why:

Statistics don’t have feelings. Google Translate is based on statistics — it chooses the “best” translation based on how certain words and phrases have been translated in other documents. As a result, machine translators choose the most probable translation, but not the most interesting or poetic one. As a result, even if translations are accurate (which they often aren’t), they adopt a robotic, lifeless tone. It takes a human translator, with feelings and creativity, to reproduce the tone, color, and vibrancy of the original text.

Machine translations struggle with complex grammar. Language is based on rules, and as a result, a statistics-based translator like Google will struggle with complex grammatical concepts, such as the difference between the imperfect and preterite past tenses in Romance languages. This is especially true given that Google almost always uses English — a language that does not grammatically distinguish between preterite and imperfect tenses — as an intermediary step when translating into Romance languages. Therefore, Google Translate often incorrectly translates the imperfect past as the preterite past (and vice versa), making ongoing or habitual acts seem like one-time, completed events.

Google can’t write for an audience. Every translator knows that you need to tailor your work to whom you’re writing for. For example, if this article were written for a casual blog, my use of the word “whom” in the previous sentence may come off as overly formal. However, given that this article appears on a language interest blog, grammarians and language experts may applaud my correct distinction between “who” and “whom” (though they may scoff at my decision to end a sentence in a preposition). Machines cannot make such judgment calls — Google cannot take into account who the intended audience is for the article it translates. Only a human translator can make that kind of decision.

Google Translate vs. a human being

To illustrate the difference between Google Translate and a living, breathing human translator, I will employ both to translate the following text in English, which appears on a website selling Argentine wine. Try to guess which one was written by a human, and which was produced by a machine (spoiler alert: it won’t be hard).

If you’re selling wine, you’d better hire a professional translator. Image via Davide Restivo / Wikipedia

If you’re selling wine, you’d better hire a professional translator. Image via Davide Restivo / Wikipedia

Original text:

Después de una excelente cosecha como la que le precedió, la cosecha 2009 muestra sus virtudes en este vino base Cabernet Sauvignon, mas el ensamble de tres variedades de gran personalidad que encontraron en San Rafael el terruño ideal para la expresión de sus mejores cualidades. Vino aun de color rojo violáceo intenso a pesar de los años en botella, ya en la copa se nos muestra intenso y seductor con aromas especiados que se entremezclan con nítidos y frescos aromas a frutas de ciruelas, cerezas negras y moras, mientras que se van desprendiendo lentamente los aromas tostados que recuerdan a granos de café molidos.

Translation 1:

After a bumper harvest as that which preceded the 2009 vintage shows its virtues in this cuvée Cabernet Sauvignon, but the assembly of three varieties of great personality that found in San Rafael ideal for the expression of his best qualities terroir. Wine intense purplish red even though the years in the bottle color, and in the cup shows intense and seductive with spicy aromas mingle with crisp, fresh fruit aromas of plums, black cherries and blackberries, while van slowly peeling roasted aromas reminiscent of ground coffee beans.

Translation 2:

After a great harvest like the one that preceded it, the 2009 harvest shows its virtues in this cuvée Cabernet Sauvignon. It’s an expressive mixture, articulated by three varieties of great personality that are found in San Rafael, the perfect region to bring out its best qualities. The wine still preserves a strong purplish-red color, in spite of the amount of years gone by since it was bottled. Once poured into the glass, it remains intense and seductive. Its spiced scents mix together with clear and fresh fruit aromas of plum, black cherry and blackberry, while its toasted scents release slowly, reminiscent of the delicious smell of ground coffee beans.

You probably guessed right: the first translation was done by Google; the second, by a professionally trained bilingual translator. As you can see, the machine translation is barely comprehensible: it contains grammatical gaffes such as run-on sentences, wrong adjective order (e.g., “wine intense purplish red”), and sometimes just failed to translate words altogether (e.g., “van”). On the other hand, the human translation flows smoothly, is organized coherently, and matches the elegant tone of the original article.

Machine translation isn’t without its perks. It can be a life-saver in a pinch, when you need to get a rough idea of what a certain phrase means, or when you need to decipher a street sign while traveling to a foreign country. However, when it comes to translating important documents, the limitations of machine translation prevent it from being a viable option. As the above examples demonstrate, a translation that is based on statistical patterns will never match the quality of one created by a professional, who understands the rules and nuances of language. Indeed, machine translation has come a long way, but it’s still far from replacing the human touch.

The following post is from Paupaul_thumbnaill, an English teacher who lives in Argentina. Paul writes on behalf of Language Trainers, a language teaching service which offers foreign language movie reviews as well as other free language-learning resources on their website. Check out their Facebook page or send an email to paul(at)languagetrainers.com for more information.

Go Back to School en Español with New Spanish Elementary Lessons

Posted on 31. Aug, 2015 by in Company News, Language Learning, Product Announcements

Online technology has opened up a world of opportunities for teachers and homeschooling parents, but there’s a lot out there in that world that you can’t control. Even in educational technology, it’s sometimes hard to know what you’re going to get. If you’re teaching grade-school students, you have to be particularly careful with language learning applications – you don’t want to end up with vocabulary lists full of age-inappropriate material such as “Would you like a beer?”, nonsensical phrases like “I have the small pig on my knees.”, or questionable content such as “Don’t teach your grandmother to suck eggs.” (Yes, we’ve seen all of those in actual language-learning products!)

Fear not, there are no egg-sucking grandmas in our new Spanish Elementary lessons. Specifically designed for children between 6 and 11, the 68 lessons in the Spanish Elementary series teach age-appropriate words and phrases that elementary students actually say, covering topics like making friends, classroom objects, and birthday parties. They include all of the basics (colors, numbers, and so on), but no more adult content—not even the PG stuff like booking a hotel room or buying a plane ticket. Because, let’s be honest, when was the last time your 6-year-old booked him- or herself a room?!

elem spanish3

The 68 lessons are divided into 3 levels of increasing depth and duration, all appropriate for young, beginner learners. For example, the “Hello” lesson in Level 1 covers a handful of basic greetings, while the “Getting to Know You” lesson in Level 3 expands on those by providing additional salutations and longer phrases. You can have your students complete the levels in order, or skip around according to their schedules and skills.

Elem Spanish1

Whether you’re a classroom teacher or the parent of a homeschooled child, the Spanish Elementary lessons provide the ideal environment for your students to practice listening, speaking, reading, and writing Spanish words and phrases they’ll actually need and want to know.

Register for our free trial to test it out for yourself, or contact us for more information. Already registered? You can access the Spanish Elementary lessons by clicking the Browse button in your Learning Path and opening the Supplemental Vocabulary tab.

By the way, if you’re an adult Spanish learner at the beginner level, you’ll enjoy the rest of our offerings in Transparent Language Online, including the Essentials course! You can try them all free here.

Staying Resourceful in Language Learning

Posted on 26. Aug, 2015 by in Uncategorized

Itchy Feet: Resourcefulness

Do any of the following sound like they might have come out of your mouth at one time or another?

“I know drilling grammar is important, but it’s just not fun…and life’s too short.”

“I can read street signs and menus, and understand when spoken to, but I can’t speak it. I just can’t find the words to put a sentence together.”

“I’d really like to learn this language, but it’s so time-intensive, and time is the one thing I simply do not have.”

“I’ve plateaued. For me to improve from this point, I’d have to go live in a country where it’s spoken natively. How in the world am I supposed to do that?”

Every single one of those fabulous excuses has come out of my mouth before, and they’ll probably cross my lips again. That’s how I know they’re so fabulous. They’ve successfully allowed me to spend my time and energy on what really matters: binge-watching the latest TV series (to get it out of the way, of course!). Sometimes language learning is hard work, and that’s a bummer, so why bother?

Well, the other day I came across the comic above, and it made me realize that there’s another way. We can be resourceful.

Humans are extremely resourceful creatures. We’ve learned to survive in nearly every corner of the globe, from blazing deserts to freezing tundras, and–who knows–may soon be colonizing other planets. That requires extraordinary resourcefulness. When we undergo a large, destabilizing change in our lives, we’re usually able to re-stabilize in a matter of months. We’re smart, we’re fast learners, and we can use our environment to better purpose our needs. And you don’t have to be a super-genius to have those abilities–you were born with them, baby. And the best part is, they’re not just for survival. You can choose to make use of them in your everyday life. You can use your own resourcefulness to learn languages.

The key is remembering what resourcefulness is: recognizing a challenge, seeing it from a new angle and devising unique means to meet that challenge.

Let’s apply it to the four fabulous excuses above.

You know you need to drill grammar to get better. You can’t just absorb the knowledge by living in the same room as your grammar book, you actually have to do the work. Step one, recognize the challenge: it’s soulless, tedious work. Step two, see it from a new angle: it wouldn’t be tedious if it were fun, right? Step three, devise the means to meet it: make a board game out of the declension tables or a card game out of verb conjugations. Play with friends or share it online. Or, reward yourself for time studying with a piece of chocolate every time you get something right. Make it different kinds of chocolate for different answers, so you’ll be using your tongue to help you remember.

Just how resourceful you can be is up to you, of course. You’re only limited by your problem-solving abilities, which if you’re human, are already pretty impressive. Let’s keep going.

The challenge: despite the fact that you can read signs and understand what people are saying to you, you “can’t find the words” to put a sentence together yourself. See it from a new angle: sounds like you do have the words, you just don’t have the nerve. You haven’t talked the walk. You probably haven’t even tried that hard! Do you realize how long it takes children to learn to speak? First they have to make the mistakes, you know. That’s the only way. Devise the means to deal with it: make a weekly chart with checkpoints to mark your progress. Start small, like “order in a restaurant,” or if you’re past that, “introduce myself to a stranger.” Maybe have a system to reward yourself at the end of the week if you passed one of these checkpoints every day. Or, team up with a friend also learning the language and go out together. Challenge each other to go further in a conversation with a local, and whoever can top it buys the other a round of drinks.

Games and rewards are certainly one way to be resourceful, but I’ll bet you can think of others. If you’re reading this, you’re already quite resourceful, did you know that? Let’s continue.

Challenge: ain’t got no time nohow to learn that there new language. New angle: really? No time whatsoever? Or just no will to make it work? Means: wear a colored bracelet twice a week to remind yourself to spend every free second on your new language. Use language software or apps or plain old flash cards on the subway, buy yourself a kid’s book in that language, and find a local restaurant from that culture that you can start to frequent. On the days you’re not wearing the bracelet, you don’t have to worry about it. Or, sit down and actually calculate out your week, and see how much time you spend doing stupid things. There’s nothing wrong with that…it just means you choose to spend your time differently. Would you like to change it?

As you can see, the possibilities are endless. Resourcefulness helps you dig up the willpower to find a way to accomplish your goals. Don’t let them just sit there empty; identify the challenge, look at it from a new angle, and devise the means to meet the challenge. Let’s move on to the final one.

Actually…why don’t you tell me some resourceful ways to deal with quote #4? What are some creative ways to manage plateauing in a learned language? Leave your thoughts in the comments. We’re just spitballing here, people. No wrong answers, just inspiration!