Combining software with human intelligence to improve translation

/in , /by

Translation graphic

Stanford computer science graduate student Spence Green is first author on two studies about blending human and machine intelligence for language translations.

Computer scientists at Stanford have created a language translation system that allows bilingual humans to translate text faster and more accurately than is currently possible.

This hybrid approach, which blends human and machine intelligence, is aimed at the $34-billion-a-year worldwide market for professional translation services.

The work is the focus of a dissertation by Stanford computer science graduate student Spence Green and is part of a machine translation research effort led by Christopher Manning, a professor of linguistics and of computer science.

The authors presented their hybrid approach to translation at two computer science conferences in October.

As Manning explained, software-based language translation was among the first applications tested on the computers developed during and after World War II.

“During the Cold War there was a great desire to understand the other side and doing translation by computer seemed a natural parallel to computer-based cryptography, which had been successful,” he said.

Christopher ManningChristopher Manning, Stanford professor of linguistics and of computer science, is leading research into computer-assisted translation.

But while computers were great at breaking codes based on rules, they proved unable to resolve the ambiguity inherent in human languages. In recent years, however, advances in machine learning, coupled with the proliferation of text on the Internet, have helped improve fully automatic machine translation. Today, online tools like Google Translate can be used with foreign text to get the gist of the meaning.

But when precise and nuanced translations are needed, such as in preparing international business contracts, firms generally hire bilingual human translators.

Yet even professional translators use machine-based systems as a starting point in a two-step process. First the human uses automatic machine translation to create a rough translation. Then the human translator performs a post-editing step to render an accurate final version.

The Stanford approach combines both steps – the quick machine effort and the nuanced human translation – into one faster and more efficient solution.

“Our system augments the human translator and increases efficiency, accuracy and productivity,” said Green, who was first author on the research papers.

A human translator translates an average of 2,800 words per day, or about seven single-spaced pages.

To improve that productivity, the Stanford system provides the human translator with an interface that resembles a word processor. When the translator begins typing a translation, the system generates suggestions for key words and phrases that could have multiple meanings. Crucially, the system revises its suggestions in real-time as the translator works, fine-tuning the software and improving the quality of its assistance.

“A key challenge is to design an interface in which people and machines can work together to produce a translation,” said Jeffrey Heer, a former Stanford faculty member who was involved in the project. “How should the machine suggest edits without interrupting or overwriting a person’s work? How can a person guide the machine towards better translations?”

Martin Kay, a professor of linguistics at Stanford and an expert on computational translation, framed the nature of the challenge in his seminal 1980 paper, “The Proper Place of Men and Machines in Language Translation.”

“When I wrote this article, I was convinced of two things concerning computers and translation,” Kay said in commenting on the new hybrid system. “One was that there would surely be many roles that computers would be able to fill; second, that automating the whole process would not likely be one of those roles.”

Kay, who was not directly involved in this project, called the new hybrid system “a magnificent example of how human-computer cooperation might be engineered.”

Other team members include Heer, now a professor of computer science at the University of Washington, and Stanford graduate students Jason Chuang, Sida Wang and Sebastian Schuster.

The authors describe their hybrid system in two scholarly papers.

At the User-Interface Software and Technology conference on Oct. 5, they presented a paper on their interface design, which resulted in higher quality final translations than standard post-editing systems.

At the Empirical Methods in Natural Language Processing conference on Oct. 26, the team showed how the machine translation system can use feedback from the human translator to correct mistakes and even adapt to his or her style. This novel advance could lead to personalized machine translation, where each translator has a custom system that learns his or her individual preferences.

Original article published here: Stanford News

Google+
Facebook Follow
Twitter Follow

Localized Slogans: When Language Translation Gets Tricky

/in , /by

A slogan. It seems pretty straightforward. Translating a couple words or even a sentence shouldn’t be all that complicated, right?

And yet we’ve seen countless examples of mistranslated slogans—from big global brands—that illustrate just how tricky translating slogans can be.

Anybody recall Pepsi’s “Come alive with the Pepsi generation” tagline being translated into “Pepsi brings your ancestors back from the grave” in Chinese?

While humorous, this language translation misfortune can be costly—and not just in a monetary sense. We’re talking time to market and brand reputation costs, too.

Why slogans pose language translation difficulties

The very nature of slogans makes them challenging to translate. A lot of times slogans are very creative, playing on cultural idioms and puns.

Word-for-word translation can be difficult in this case. There often isn’t a direct translation that can take on the exact meaning of your slogan.

Local nuances come into play as well. Some words may have entirely different meanings than your source language and can be misinterpreted. Just think of product names that are often used in slogans. The Chevy Nova name was criticized in Latin America because “Nova” directly translates into “doesn’t go.”

Also, different cultures have unique emotional reactions to given words. Take McDonald’s and their famous slogan “I’m lovin’ it.” They localized it to “Me encanta” or “I really like it” so that it was more culturally appropriate for Spanish-speaking countries, where love is a strong word and only used in certain situations.

Because of the complexities involved, you may need a more specialized form of language translation to ensure that your slogan makes a positive impact in your international markets.

How to approach slogan localization

First and foremost, communication is vital throughout the entire localization process. When approaching slogans, your language service provider will collaborate with your marketing experts—whether internal or outside creative agencies—as well as your in-country linguists with marketing expertise.

Having in-country linguists work on your slogan is absolutely critical. These language translation experts are fully immersed in the target culture. They are cognizant of cultural nuances, slang and idioms, which ensures that your slogan will make sense—and go over well—in your target locales.

They’ll review the concepts in the tagline or slogan as a team and identify any challenging words or phrases and assess how to approach it. Oftentimes, a direct translation won’t work. You may need to localize it in a way that’s more appropriate, such as the McDonald’s “Me encanta” example above.

If it poses much difficulty, then you may need to turn to transcreation services.

Transcreation and your slogan

Transcreation is a more specialized version of language translation that’s a highly involved and creative process.

Copywriter linguists will identify your brand qualities and portray those in a way that perfectly resonates with your target audience. Think of it as a mix of “translation” and “creation.” It’s not a word-for-word translation, but rather re-creating an idea or message so that it fosters an emotional connection in a different culture.

Let’s look at an example. Nike’s celebrated slogan “Just do it” had no meaningful translation in Chinese. So instead, the message was transcreated to mean “Use sports” or “Have sport,” which had a more prominent impact.

Localizing your slogan correctly can mean a stronger global brand reputation—driving revenue and increased market share worldwide. Taking a hasty, nonchalant approach can mean just the opposite. And you may find yourself having to spend time and resources rectifying what comes with a language translation error.

Original article published here: Business 2 Community

Google+
Facebook Follow
Twitter Follow

How the Nuremberg Trials Changed Interpretation Forever

/in , /by

Lynn Visson was a UN interpreter during the height of the Cold War. She can still rattle off grandiose Soviet titles like it was yesterday.

“General Secretary of the Central Committee of the Communist Party — you had that practically memorized,” Visson recalls.

After 23 years, she’s still at it, interpreting from French and Russian into English. She’s witnessed — and spoken for — some pretty heavy hitters. “I remember Castro spoke for all of eight minutes, but the charisma was incredible,” Visson says. “The electricity the man generated — Bill Clinton could do that, too, Gorbachev could do that. Some other delegates were great speakers, but they didn’t light that spark.”

These days, we’re long used to seeing diplomats at the UN plugged into earphones, listening to speeches that are instantaneously translated into one of the six official UN lanugages — English, French, Arabic, Chinese, Spanish and Russian, but simultaneous interpretation is actually a rather recent invention, developed in 1945 for a very different global event: the Nuremberg Trials.

Before the Nuremberg Trials, any kind of interpretation was done consecutively — talk first, and then wait for the interpreter to translate. But at the end of World War II, the Allies created the International Military Tribunal, which was charged with an explicit mission: “fair and expeditious trials” of accused Nazi war criminals.

“Those two words put enormous constraints on the people organizing the trial,” says interpreter and historian Francesca Gaiba, who has studied the origins of simultaneous interpretation at the Nuremberg Trials.

She says holding a trial that was “fair” and “expeditious” meant speeding up translations of the four languages of the nations involved: English, German, Russian and French. The solution was thought up by Col. Leon Dostert. Born in France and a native French speaker, Dostert became an American citizen and a foreign language expert for the US Army.

“He was the person who thought it was possible for a human being to listen and speak at the same time,” Visson says.

Possible, yes, but far from easy. And then there was the problem of transmitting all of those languages in real time. This was 1945, so digital recordings and tapes weren’t around. But Dostert pressed on and consulted with IBM to develop a system of microphones and headsets to transmit the cacophony of languages. He hired interpreters and practiced this new type of interpreting with them.

And somehow, despite a few episodes of tripping over cords in the courtroom, Dostert’s system worked.

Even before the Nuremberg trials were over, Dostert had taken his system to the UN in New York. It’s still the model being used today, albeit with some minor upgrades in technology.

“When I started, all interpreters were lugging around heavy dictionaries,” Visson remembers. “Now they’re lugging around iPads and notebook computers because most glossaries are in those.” She says TV monitors in the back booths also let interpreters watch the expressions of diplomats and the movements of their mouths.

But technology still hasn’t advanced enough to replace the interpreters themselves. “The computer can’t pick up the intonation,” Visson says.

But one of the biggest challenges for interpreters is often not the tone, but simply figuring out what a diplomat is saying.

“People with foreign accents for example, you want to be careful that when you hear somebody saying, ‘Mr. Chairman, we wish to congratulate you on your defective leadership.’ You know he didn’t mean his ‘defective leadership,’ he meant his ‘effective leadership.’” Visson says. “But you’ve got to not be simply auto-translating word for word, because heaven help you if you say we congratulate you on your defective leadership.”

Of course, relaying the words of world leaders also means not mincing them, be they Holocaust denials, carefully crafted insults or strongly worded Cold War rhetoric.

“One of the things you are taught is that you’re like an actor on stage,” Visson says. “There are plenty of actors who play the part of people who are absolutely vile. So I think if you look on it as acting, it can almost become fun — even if you are saying things that you personally find repugnant or hateful.”

Original article published here: PRI

Google+
Facebook Follow
Twitter Follow