The Danger and Impossibility of Machine Translation

The Danger and Impossibility of Machine Translation

If you have ever played around with Google Translate (Yahoo翻訳、Excite翻訳、etc) you know that it is far from reliable. So I was very surprised when I heard, through a friend who attended the JAT presentation  “Does Translation Pay the Bills?”, that machine translations and native checkers are quickly replacing actual freelance translators. This is ridiculous. If you have ever tried to translate anything highly technical, you know that Google doesn’t cut it. But, I am sure they are not using Google. So the question is:

How far has machine translation come?

The answer, I have found, is not very far. Machine translation is light years away from where it was when the internet was first getting started and everyone was laughing at the kind of things Babelfish came up with. But, it is far from perfect. The general consensus in the market right now is that, even if you buy the most expensive software out there, the product will still be inferior to what a native speaker can produce. The reason is that language is just incredibly dynamic. Take the word 対応 for example. The dictionary has this as “correspond to”. However, it can function in an English sentence as “for”, “support”, “handle”, “tackle”, “address”, or (my favorite) NOTHING. There are times in translating when a word in the original simply has to be omitted. It happens with words like 対応 in Japanese and with pronouns in English. While it is perfectly acceptable in English to say “I put my homework in my bag”, it would be ludicrous to say   私は私の宿題を私のかばんに入れました. Just not necessary. Yet if you Google Translate the previous sentence, you come up with an odd variation. 「私は袋に宿題を置く」This shows a different problem: Lack of understanding of context. Any beginner student of Japanese would have been able to handle that sentence. Yet Google decided to use the more common translation of each word (袋 and 置く).  This is the heart of the problem. Translation software cannot assume it knows what you are talking about (as translators do). You have to spell it out. Oddly enough, if you take the ludicrous Japanese above and go J>E, you end up with “I was put in my bag with my homework.” Closer. Take out the 私は and you get: “I put in my bag my homework.” Now we have the second core issue: Word order. Google Translate has obviously been programmed with the correct STPOQV word order. However, it can’t always understand how that correlates to English sentences. It also doesn’t understand when someone breaks grammar rules. It can’t assume subjects correctly when they aren’t there. I shutter to think what it would to with languages that have a truly flexible word order. How can it know whether the beef ate the man or the man ate the beef?

I am not saying that machine translation will never be wide spread. As I learned, it already is. But one thing is true. It will never replace translators, particularly in one very important field:

Literature

You cannot sell machine translations of literature. (That is a bold statement but let me elaborate.) MT is enough to get by. You get the point of what you are reading and that is why it is common in legal and science translation. But people read novels for the experience. They want the story and the art of the language transferred into their own. Their are countless stories of beautifully translated phrases that became as famous in the target language as they were in the original because they were delicately re-crafted to evoke the same feeling as the original with different words. 「君の瞳に乾杯」has to be one of my favorites. “Here’s looking at you kid.” Same feeling, different words. That is what literature (in that case cinema) needs and that can never be done by a computer.

Advertisements
The most amazing way to handle large numbers when interpreting

The most amazing way to handle large numbers when interpreting

Like everyone else who learns Japanese, I had trouble when the teacher first introduced 万. Seriously, you want me to count in ten thousands? But I became adjusted to it, especially after living in Japan.

Still, that could not have prepared me for the incredible pain of interpreting numbers thrown out in business meetings. Even when they aren’t important, people will say things like “it’ll cost us two or three million to fix this”. While you are frantically trying to rearrange the commas to make the appropriate number of 万, the conversation has progressed without you and your clients are wondering what incredibly complex word you might be trying to figure out.

This link has the absolutely easier way I have ever heard of to convert numbers. It is beyond brilliant. I think it might have fixed one of my biggest problems to date. Take a few minutes to read through it if you have ever had this kind of problem.
http://alcom.alc.co.jp/users/24029/diary/show/52423

Basically it is as follows:

一         1  one
十         10  ten
百   100  a hundred
千          1,000  a thousand
万          10,000  ten thousand
十万      100,000  a hundred thousand

100万            1,000,000  a million
1000万          10,000,000  ten million
1億         100,000,000  a hundred million

10億         1,000,000,000  a billion
100億       10,000,000,000  ten billion
1000億     100,000,000,000  a hundred billion

1兆      1,000,000,000,000  a trillion
10兆    10,000,000,000,000  ten trillion
100兆  100,000,000,000,000  a hundred trillion

Everyone is generally fine up through 10万=100,000

So, when you get past that, there is an easy trick. For the 万s, subtract two zeros and that is the number of millions you have. For example:

100万 – 00 = 1 million

6300万 – 00 = 63 million

This works until you get up to 億, so they give you an easy way to bridge the gap. You just have to remember 「日本の人口=1億3000万=130m (one hundred and thirty million)」. So if you hear 293 million and remember that phrase, you can easily convert it to 2億9300万 if you remember that phrase.

After that (10億以上) you will take the 億 and subtract one zero to get the number of billions.

50億 – 0 = 5 billion

780億 – 0 = 78 billion

 

Hizzah! Now you can convert numbers with ease!

Comparative Learning

Comparative Learning

When you want to learn how to say something correctly, you can’t always look it up. To give an example, I have been using 数量for a while to talk about the quantity of anything and everything. However, as I was translating J>E I realized that the author of the document used 個数 and it dawned on me that I have seen tons of occurrences like that but never incorporated it into my own Japanese. (枚数、件数、トン数など)

If you do J>E, the original document can be one of your best study resources ever. Because you already know what you want to say in English. You can see what you translated the original into and then remember, when you see something like that come up in your E>J work, you will know what phrasing a native speaker would use.