We often present clients with guidance on how to work with interpreters, and frequently get asked about AI. This is because many people are waiting for the day that they can simply go online and use AI to seamlessly translate between two different languages, but we would like to say it out loud here: THAT DAY HAS YET TO COME.

Please also check out this flip-book we’ve made https://heyzine.com/flip-book/20de67a12a.html

Please also check out our playlist for Chinese localization case studies: https://www.youtube.com/playlist?list=PLO-QGEbwcTr14xqfiR38Mp-EhHAmclsUY

We localized the Interpreters and Music video into traditional Chinese as an example to compare translation accuracy between humans versus AI and to identify some classic AI issues.

One of the biggest weaknesses of AI is that it often struggles with names. For instance, the name “Laura” was translated into both “蘿拉” and “勞拉.” When we saw this inconsistency in names, we looked at each other with amusement because this happens all the time. Some may say AI spelling names incorrectly isn’t a big deal since it’s an easy fix. However, for those people, we’d like to share a real-life example.

In a lease contract we worked on, Paragraph 1 said that the landlord shall be known as ‘A’ and the tenant as ‘B’. Paragraph 2 called the landlord ‘C’ and the tenant ‘D’. This was a document with 30,000 words that a client asked us to quote for reviewing the translation, which had probably been done by an AI. Just in terms of reviewing names, how much effort would it take to find out if there were places that call the landlord “E” and the tenant “F” and so on? Not to mention all the work it would take to find other mistakes that humans typically need several rounds of review to detect.

Our analysis also uncovered that AI defaults to using the pronoun “你,” referring to males and offering no female form “妳.”

AI have translated love song titles like “Suddenly Missing You” and “Stuck on You” into traditional Chinese, using the male form. The male singers may not prefer using the male form of “you” in their love song titles. Otherwise, a native speaker in traditional Chinese would feel kind of strange, reading it.

We inserted line breaks on messages that appear in the video. With line breaks, AI seemed to lose the context of the lines.

Line breaks are important. We are often requested to insert line breaks in Asian language marketing materials. Take Japanese line breaks as an example. There are some basic rules for line breaks or how to break words up, but at the same time, there are a lot of exceptions, which humans can easily catch if they understand Japanese, but not AI. In other words, humans break things apart (debriefing) and put them together in a creative way, which AI is just not capable of.

It turns out that AI struggles to translate any segment accurately and, at times, produces unnatural and contextually absurd translations. As shown in the screenshot below, even with a relatively short source text, the quality of AI translation was unbelievably subpar.

AI translated “interpretation” as “explanation” due to a lack of context.
AI translated “Performance” to machine’s performance rather than that of the interpreter’s.
AI mistakenly translated the meaning of “like” as “to be fond of” instead of “similar to.”
AI word-for-word translation for “big heart” doesn’t make sense to a Chinese audience.

It’s clear to us that AI is not able to handle messages that are broken down by line breaks. This then leads us to a question: How well could AI handle entire messages without line breaks?

We conducted a retest by removing all the line breaks on messages. In this attempt, the text was formatted in a more machine-friendly way to enhance AI’s understanding. But even so, post-editing remained an essential step, with 80% of the segments requiring significant human intervention. Without this crucial step, AI translations either come across as rigid and less relatable to our audience, or contain mistranslations. Below are some examples.

Example 1:
The AI translation appears rather stiff because the word “sync” was translated literally. The audience might wonder what it means to “sync” one language to another. Human translators are able to further explain the context of sync, that is, interpreters “listen to one language and convey it in another language.”

Example 2:
AI translated “more emotionally acute” as “more impatient,” which not only deviates from the intended meaning of the source, but also negates the impact of the word “music”. During post-editing, we replaced it with “more emotionally sensitive,” which is more contextually accurate.

Example 3:
AI did word-for-word translation again. It doesn’t sound like what a normal person would say in Chinese. As a dynamic language, Chinese favors verbs over nouns and usually keeps sentences short. Therefore, in post-editing, we restructured the sentence to make it fit a typical Chinese writing style, and flow more naturally.

Example 4:
AI’s translation of “concentration” lacked clarity. Without referring to the source, it was hard to grasp the intended meaning. So, we opted for a more precise choice of words.

Example 5:
AI does a literal translation, full of ambiguity and rigidity, which doesn’t make clear sense to a Chinese audience.

Translation is supposed to flow naturally to engage the audience. It is the more immersive and relatable experiences that make humans feel comfortable. These are exactly the areas where we as interpreters and translators can contribute to.

There may be a lot of gloom and doom from some in the community who think that their jobs are at risk, however, the reality is that we’re training AI to speak our language, but they aren’t able to fully understand it like we can. They can process it, try and find the corresponding pattern in their database, and come to a conclusion that they think is right, but they won’t always be. That’s where interpreters and translators will always have the edge over AI. Human creativity and our ability to understand what’s important, and the culture embedded in it, enables us to make sure that we are conveying the intended message.

We tried one of the latest AI platforms to translate one of our office videos into Mandarin.

While we were impressed by the seamless process and the voice cloning feature that enhanced voice modulation, we couldn’t help but notice pronunciation and translation errors in the generated video. Given that Mandarin Chinese is a tonal language, tones can become a source of misunderstanding if not pronounced correctly. The chosen video introduces the rental service of our conference room, making “conference” a high-frequency word. However, throughout the video, AI consistently pronounces the Chinese word for “conference,” as “memory,” with tones differing from the former. Also, “state-of-the-art” in Chinese is pronounced the same way that “cash” is. This could undoubtedly complicate the message we aim to convey if left alone.

The translation issues we caught are mostly recurring problems caused by machine translation as discussed above. Take the first sentence as an example. AI translated “Looking for a conference room to have a meeting over video or in person?” as “Can you look for a conference room via video or in person meeting?” AI’s rendition deviates from the original meaning, which is likely caused by line breaks, leading to confusion and miscommunication. Such discrepancies underscore the importance of post-editing and human intervention to refine machine-generated translations.

Our conclusion becomes clear.

In this age of AI becoming more prevalent, humans just need to work smarter to beat out AI. As individuals in an evolving world, it’s important to accept technological advancements, but also understand that AI lacks creativity, individuality, improvisation capability, and the understanding of human cultures. That’s how humans can break through and go beyond AI’s limitations.

1. Aren’t translators and interpreters the same?

This is a very, very common misconception. Outside of the language service provider sphere, “translator” and “interpreter” can be used interchangeably in most discussions. Such as: “We’ll need a translator at the board meeting” versus “We’ll need an interpreter at the board meeting.”

But just what is the difference between those terms? Simply enough, both “translator” and “interpreter” refer to someone who conveys information from one language to another; more specifically, a “translator” works with written words, while an “interpreter” works with spoken words. Some people are only translators, some are only interpreters, and others are both.

2. Can’t any bilingual person be a translator/interpreter?

A very common misconception (in the workplace especially) is “Billy is bilingual, so he can handle this project and translate/interpret for us.” Just because a person is bilingual (or trilingual or more, even), does not mean that they have the training required to be a proper translator or interpreter.

Imagine that “Billy” speaks Spanish at home, but grew up going to school where the primary language of instruction was English. While there’s a chance he can talk about any subject at home with his family members, a likely scenario is that he will know more about biology in English terms rather than Spanish terms. Unless the conversation were very simple, such as general conversation for travel or something similar, it would be very difficult for Billy to translate or interpret something.

Translators and interpreters go through rigorous training for their respective crafts, and have expanded their vocabularies enough to compensate. Proper translators and interpreters have high-level certifications as well.

3. I know a translator/interpreter who did Assignment X, why can’t they do Assignment Y?

In the language services industry, some translators and interpreters can fall under the category of “subject matter experts.” These people have trained to not just be general translators or interpreters, but have polished their skills to cater to certain types of work.

Take “Billy” from above, for example. Imagine he’s become passionate for being an interpreter, and his other interest in biology spurs him to an interest in medical interpretation. After enough study, focus, and—of course—certification, he becomes a proper medical interpreter and specializes in speaking between doctors and patients about surgeries. He might be able to do general interpretation as well, but because of his deep specialty, he might have trouble if he suddenly needed to interpret for, say, a lawyer discussing a lawsuit.

Just like how doctors and lawyers require separate studies, medical interpreters and legal interpreters also require focused study in their area of expertise. They may have skills that overlap, but generally, it’s best to rely on separate translators/interpreters who are subject matter experts rather than the same one for every single job.

4. Wouldn’t machine translation work well enough?

Short answer: No.

Long answer: Machine translation can certainly help a translator do their work. Computer-assisted translation tools (called CAT tools in the industry) can keep a handy glossary of terms for the translator, and have the memory to provide reference for older, similar translations.

But if we rely only on machine translation, any number of problems can happen. Machines think very differently than humans and might misinterpret context, homonyms, word register, and so on. Computers may be able to perform complex mathematical calculations, but the human brain is hardwired for language. Put simply, a translation from a human is going to sound a lot more natural—and have fewer mistakes—than a simple machine translation.

5. Why does a translation need proofreading? Shouldn’t the translator be enough for that?

Speaking of “mistakes,” mistakes happen. To err is human, after all. Translators need proofreaders for the same reason that a journalist, book writer, or a lawyer needs one. Mistakes concerning facts, grammar, spelling, etc. can easily be made by any sort of writer, and the same goes for a translator.

Having a second pair of eyes does wonders for any written work. A proofreader for a translation can catch errors in spelling, word register, a forgotten period or comma—anything that might have slipped through the cracks. If you want a translation to be as polished as possible, having a proofreader is essential.

A friend once asked me if I believed that my career was in danger of being outsourced to translation technology. In other words, he wondered if I felt that my profession was threatened by advances in machine translation, whereby potential clients can simply enter their text in a computer and  – voila! – an instant translation appears before them.

I told him that while technology certainly has its merits, true quality in translations can only be achieved through human attention to detail, human patience, and human passion. After all, how can a computer possibly convey the subtleties and feeling contained in a text produced by a human being, whose very essence is manifested in the words that he or she has written?

So no, I am not worried that my profession – and moreover my passion – is in danger of being made obsolete. On the contrary, I believe that every time a client of mine receives one of my translations, he or she will understand that my work, like that of an artisan whose livelihood could never be replicated in a factory, exudes the quality that can only come from the hands of a human being.

These thoughts on quality brought to you by our translator Mac Layne.

Explore the fun between human and animal communication in different languages!

Unless you were lucky enough to grow up speaking multiple languages, learning a whole new one can be an extremely difficult task. Still, people are willing to put in hundreds of dollars and hours in order to officially call themselves bilingual.

However, we aren’t the only ones capable of achieving this feat… animals are too, and it’s quite a bit simpler.

Avid Scooby-Doo fans know that our animal companions will do practically anything for a tasty snack, and that includes learning new and already-known commands in a different language. By assigning hand gestures with a command in the desired language, your dog will eventually be able to respond to the word or sentence in both languages simultaneously without the need for hand signs or body language.

If you want to see a bilingual dog in action watch this video of a man who taught his dog multiple commands in both English AND Japanese: http://www.youtube.com/watch?v=qdDMvXCeaN8