Categories
Observations

Skype Translation

Instantaneous translation will soon be available for people conversing on Skype. Presumably, the first phrase that the computer will have to learn is “can you hear me?”. But what impact will this have on Bible translation?

The idea that you could speak into a device in one language and it would emerge in another has long been a sci-fi fantasy. But this week that kind of automated translation came a step closer to reality when Skype launched the beta version of its Translator service.

So writes the BBC technology correspondent, Rory Cellan-Jones.

Currently the service is an invitation only trial and only works between English and Spanish. While the service isn’t perfect, it is clearly an impressive piece of technology and will only get better over the years. This report prompted a couple of thoughts:

Skype will need to deal with connection problems before the translation service will be much use. Anyone who has tried to have a Skype conversation (especially with someone in the developing world), knows the frustration of falling connections and freezing video. Presumably, the translation adds another step and additional computing demands on the call; this can only make things worse. The big problem with Skype is that it is almost perfect. It offers and amazing service, but it falls over just often enough to make it a pain in the neck. I assume that the first phrases that Skype will have to learn in any language will be; “can you hear me?”, “you are breaking up” and “can you repeat everything you just said?”.

This won’t make Bible translators fear for their jobs anytime soon. As the original report says:

In any case, Skype’s Translator and its rivals have some way to go before they can match the abilities of a skilled human linguist. You would not want them involved in vital negotiations between world leaders for example.

Not only that, but the technology relies on their being a huge amount of translated text already available, to build up the translation service:

But it seems it is not a question of getting the machine to learn like a human. “It’s not like someone who goes to school and learns a language by learning the rules,” Vikram explains. “Computers use a different approach. They take large amounts of parallel texts – high-quality translated texts – and then use that text to build a probability base language model.”

Computers, then, are living off the work of human linguists, scouring the web for examples of translated text. If this blogpost is translated into other languages, for instance, it could help feed translation engines of the future.

I commented on this feature of instant translation in a blog post five years ago.

In other words, the model for doing translation is built on translations which have previously been done by humans. What is the text that is most often the first to be translated into minority languages? Yes, you’ve got it, the Bible (or sometimes the UN declaration of human rights). So, in order to do an instantaneous translation of the Bible, we will need to load up the system with a translation of the Bible. I don’t actually see much of a short-cut here.

There is undoubtedly a massive future ahead for machine based translation, but it won’t have an impact on most of the world’s 6,000+ languages anytime soon.

Yes, I know the photo on the front page for this article wasn’t of a Skype conversation; but it was all I had!

 

7 replies on “Skype Translation”

Comments are closed.