Now you’ll be able to understand what Zee Germans yell when they score a goal
Check your calendar, friends, for the first time in a long time I was just wowed by a tech story. Google says it’s working on smartphone software that would automatically translate foreign languages into your native tongue. So, if you’re talking to your Venezuelan pen pal, and he says, “No me gusta el fútbol americano,” you can react in horror as you try to explain to him the importance of a game where more time is spent setting up plays than actually executing them is the greatest sport in the world. Porqueria.
If all goes according to plan, the software could be ready in just a “couple” of years, which is to say Google has no idea when it’ll be ready for public consumption.
You’ll recall that Google already has a fairly robust translation software suite, and it’s totally free. It’s not entirely machine translation, though, which is generally rubbish, since people can help contribute with certain words and phrases that might not mean what the literal definition suggests.
Like, I just used the word “rubbish” to mean that machine translation is not always very accurate, not that it’s refuse.
All part of Google’s plan to ensure that humanity is fully dependent on its services, I suppose.
Here’s a tip: learn Spanish or French or Italian in high school, and you can pretty easily pick up any other romance language with not too much effort. Spanish and Italian and Portuguese are pretty much “mods,” to use a PC game word, of Latin, so it all works out.
Maybe you need one of those. “workong”? =p
Good luck to Google with their planned translator phone. I think they have underestimsted the complications they face!
My money is on a non-technological solution – Esperanto.
http://www.facebook.com/learn.esperanto < Here's a starting point ;)
It would take a lot of work to do and be fairly buggy.
As a professional literary translator, I can tell they have completely misunderstood the nature of human language. It is not very logical (perfectly logical languages may be good enough for computers, but not for people – goodbye, Loglan!), and it’s basic unit is not the word but the phrase; and constructing a complete list of phrases just isn’t possible. Esperanto seems to have found the best balance in so far between logics and humanity.
“…and it’s basic unit is not the word but the phrase; and constructing a complete list of phrases just isn’t possible.”
Well, you nearly managed to convince me that no one can speak any language. ;-)
I’m sure you don’t mean that phrases are structureless.
Actually, I think that if you are talking about what is common to all human languages, then the basic unit is the metaphor – a mapping of a unit of speech (of whatever size) to a portion of our perceived (by one of our senses) reality. Until the machine deals on this level, there will also be a mismatch between what the machine is doing and what the human is doing. There are lots of clever shortcuts out there to deal with this mismatch, however, with some relatively impressive results.
Just buzz, probably.
I think google might know what it’s doing more then some of the people above… Who knows, maybe it will work maybe it won’t. But to dismiss it entirely without knowing their exact plans, is ridiculus.
Nicholas, on your last paragraph:
you are retarded.
Go study.
For a machine translation system the language doesn’t have to be strictly logical.
State of the art systems don’t use rules to translate. Basically you just need occurence probabilities for words in a surrounding context.
So if you have enough data of texts including their translations you can ‘generate’ a stochastic model of the language and use this for the translation.
The more data you have the better your model and the translation will be.
Since Google is collecting more and more data I think this is promising.
Does google have their own speech recognition software or do they use a third party plugin, such as dragon?
Pretty sure they have their own engine.
I think I already saw this demonstrated at WES 2008 with the keynote speaker. He was taking pictures of a book and it read him the book in English then French then German.