Augmented Reality Language Translation

Life Technology
21

We’re not talking about eloquence in translation here, we are talking about getting across functional semantics. That will happen extremely quickly. I tried the app and it works OK for Spanish to English. My Spanish is very basic - AP Level highschool with no real practice since, but to me it worked.

As for replacing human translation altogether, the crowdsourcing will get better, as will the machine translations. There are only two real limiting factors to having the machine able to this perfectly: Horsepower and connection speed/reliability.

In mobile, batteries and heat are bounding horsepower. Pace of carrier investment bounds connections. These connections are needed to off-board heavy processing to a bigger machine “in the cloud” and then get back the result on the mobile.

Dragon’s Dictation on the iPhone/iPod/iPad is better than the desktop version because it off-boards all of the computation to a big machine somewhere else.

There are many computers in the world today with enough horsepower to do perfect translation better than any human can in terms of speed and error rate. The things keeping these machines from being accesible for this purpose is the direct cost of running that horsepower, the opportunity cost of what else that horsepower can do, and thus the fact that giving the public access to these machines in exchange for looking at ads is not commercially viable right now.

Thus, take into account that a Google Translate request is running on a server instance that has about the same amount of processing power and memory as a high-end consumer desktop, and that machine has to serve thousands to tens of thousands of these concurrent requests.

Also, take into account the sheer body of brain power being committed to the “semantic web”. From what I saw while in Boston, it seemed a sizeable percentage of Harvard & MIT etc. math and computer science hotshots were doing some work in this space as are others coming from the top research universities in the world in that space. As this gets better, the meta information on passages gets better and thus machine translation gets better.

It’s hard to guess how soon before we see translation of the most nuanced passages and writings totally automated, but it’s inevitably going to happen. One thing to keep in mind to put this in perspective is that personal computers in the home have only really existed for a bit more 25 years and in any real consumer penetration for a little more than 15 years. Oh and once again, that mobile as real platform has only really existed for around 30 months.

22

Yeah, but a similar effort has been going on, as I mentioned earlier, for 10 years or more on the Web, and was aimed only at “professional translators”. The results are horrible, because there is no limitation on who can decide he is a “professional translator” and participate in that site – well, except that anyone who suggests that not all opinions about a translation are equal will be booted off the site! :no-no: Now take that crowdsourcing triumph and open it up to everyone who’s ever had an English lesson, or thought of having one.

I don’t know about the FIGS languages, but between the sheer number of non-native speakers of English who would probably get involved in the Chinese>English area, plus the persistent belief on the part of many Chinese that “we can learn English perfectly” – I’m not terribly certain what would prevent such an effort from sinking to the level of the various Chinglish sites that already exist, with translations like “fried face” for “fried noodles”. You can argue that it doesn’t matter for casual use, but living in the US and observing the average IQ around here – “fried face” might be taken seriously. :doh:

23

Besides, with cloudsourcing you can throw any possibility of a coherent translation out the window, because a document will be broken up and each translator will not know what the other part of the document is, so you may have two different translations of “Sawtooth Sword” (like in a game) even though they are referring to the same item!

This is the reason why software localization firms would never consider cloudsourcing that work… the result will be a nightmare!

24

But crowdsourcing doesn’t just mean having a bunch of people contribute bits and pieces to a finished work and keeping no memory of what happened or the outcome. The semantics of word patterns themselves are being culled from the entire body of work that can be connected to the internet. The point is that basically the crowd helps the machines get smarter until eventually the machines are almost always right and no longer need people’s help.

Let’s also not forget different computing architectures such as using highly parallel processors like graphics processor units for general purpose computing “GP-GPU” are at their infancy. Certain computers will become architected more similarly to the human brain. It’s at this point that the machine beating the human in adaptive pattern matching tasks such as translation becomes inevitable.

If Kasparov’s defeat by Deep Blue proved anything, it’s that the machines will get better than people at almost any task humans spend effort to make the machines good at.

25

I’m looking for one that will translate all negative comments into positive ones.

26

[quote=“mabagal”]
If Kasparov’s defeat by Deep Blue proved anything, it’s that the machines will get better than people at almost any task humans spend effort to make the machines good at.[/quote]

Except that chess is a simple game with few rules and no opportunity for variation, compared with human language in general and Chinese in particular. Writers regularly “break the rules” and it takes a human brain to correctly interpret the meaning. That’s not true in all cases – there are cases of simple, repetitive texts on which this sort of MT might work – but in my experience over 10 years of using computer-assisted translation tools, you just don’t get many good matches for Chinese>English work. Even formatting differences can prevent the program from finding matches.

27

I haven’t used Pleco much on the iPhone (bought the live view upgrade), but just tried it out on the iPad. Impressed all over again. It’s a better experience with all the extra screen real estate. Still looks like an early Windows interface, but cool stuff all the same.

28

In terms of translating Chinese to English, there is another important problem, in that Chinese needs to be parsed before it can be translated.

Even in the current era, my English language wordprocessor (made by Bill Gates & Co.) will draw a small wavy line under English words whose spelling it does not recognize. It can also give me suggestions, if I am having true spelling problems.

Is there anything similar for Chinese? I don’t think so. What if you are confused about the use of a particular character in a particular context? [color=#0040BF]EXAMPLE: When do you use 做 and when do you use 作 ??[/color] Sometimes I get confused by I don’t find anyone coming up with a program to solve such problems.

Compared to the use of “commonly confused characters” (broadly construed) . . . . . the issue of a machine translation for Chinese to English is even much more difficult I would imagine. Hence, I would not get my hopes up.

Also, the translation of individual words or short phrases is one thing. The translation of several pages of prose is something else entirely. Infinitely more difficult to come up with something coherent.