Google Translate might not be as good as people thought | Hacker News Reader

Google Translate might not be as good as people thought

groups.google.com

109 pointsrobin_reala55 comments

Most SMT systems are trained using the procedings of the European Court - as it's a huge corpus of multilingual documents which all have the same meanings.

This is a large factor as to why non-european languages typically don't fare that well in Statistical Machine Translation systems. The corpuses (corpii?) aren't as large for other languages.

Subject-broadness is another problem. Early information retrieval systems were trained (and many still are) using the Wall Street Journal as the corpus. Which means they work great for searching on the topic of big business, but not so great on getting apple pie recipes, as WSJ doesn't talk much about that ;)

'(corpii?)'

corpores, if you must.

The plural of corpus is 'corpora': http://en.wikipedia.org/wiki/Text_corpus

slaps forehead of course it is! Thanks :)

There are some research projects (in rather early stages) that develop SMT techniques for translation to languages without big parallel corpora (essentially by bootstrapping such corpora, assisted by active learning). This could be of particular importance to keep smaller languages from disappearing, otherwise less and less works in that language will be available (yes, I'm aware that there are many people who consider language death a good thing).

Sounds fascinating; links? research? Applicability to lost languages like Linear A?

    Please apologize for your stupidity.

I wish I had the gall to say this to people

I couldn't resist: http://pleaseapologizeforyourstupidity.com

There needs to be a place to actually apologize, toss a textarea in there and show previous apologies below :)

What an awesome idea. I'm adding that to my to-do list.

So far, I'm guessing :

  lumber = log
  vomit = thow
  insult to father's stones = thrown in superclass
  wind, pole, and dragon = maybe "try,catch,finaly" or "if,then,else"
  goat-time = WTF ?

runtime maybe.

Wind in Japanese is 'kaze' (風), and the kanji character (according to rikaikun) has a second meaning: method.

http://translate.google.com/#en|ja|wind

Edit:

The kanji for dragon seems to have a reading: "ryuu" and that "sound" (if not written in kanji) has several meanings, one of which is also "method"

http://jisho.org/words?jap=ryuu&dict=edict

"goat" seems to be "yagi", and putting that in jisho.org, one of the results is related to "night shift", so maybe a nightly process? nightly build?

http://jisho.org/words?jap=yagi&dict=edict

I can't imagine anybody using '風' for 'method' for anything relating to software. It's usually written in either katakana (メソッド), or the mathematical term for function is used instead (関数).

Really wish I could see the original message...

I wish the author of that post could see a translation back into japanese of what he posted. I'd love to laugh together with him :-)

could it then be just a general "method", as in "the way to do a certain thing"?

Kind of, although I think that 'in the style of' is a more accurate translation. For example, you might see '日本風のステーキ' for 'Steak, in the Japanese style.'

I have a Russian friend who used my computer to check her vkontakte (Russian facebook), she's not used to Chrome and it auto-translated the page. At first she didn't notice because she's equally capable in English, then she started to giggle at the word pancake (which is a poor translation), but she said that on the whole it did a really good job. I guess some languages are easier to do. Anecdotal I know, but its good enough for me to use Russian websites to read photo comments.

Another interesting thing about Google Translate is that people sometimes successfully troll it by amusing the "submit a better translation" feature, which Google ostensibly uses without much checking.

I'd point out an example, but Google's engineers probably read this site, and the examples I have are too valuable for my personal amusement to give up :)

I love amusing the "submit a better translation" feature.

Thanks :) That was a fun grammar error.

Did people think it was that good? IME, it translates normal text to and from many languages into something that provides the gist if lacking in the nuances. Which, IMHO, is flippin fantastically great even in the face of the odd horrible translation.

I was recently typing in some phrases from a 19th century book in French (which I'd found on Google Books), and it was interesting to watch the translation morph as I typed and provided more context. It wasn't perfect translation in the end, but I was still pretty impressed.

Like most MT engines, Google Translate quality varies wildly by language pair. When MT is used for pre-translation in professional translation settings, it's pretty common to cherry-pick particular engines for particular source and target locales.

I did - I used it to translate from simplified Chinese to English, and the results where extremly impressive - there where very few mistakes and some of the paragraphs read like they had been written by a professional translater.

Google Translate sort of works on the premise that at least the input text isn't confusing.

If by not confusing you mean not ambiguous, then that's rarely the case in Japanese, which is a very context-sensitive language.

The original Japanese text is probably not at fault here.

There's almost no such thing as Japanese text that isn't confusing. It is a rather imprecise language. I'm not sure machine translation will ever work well.

When I worked in Germany some coworkers were trying to figure out the English word for betriebshof (bus depot) by using Altavista's Babelfish, which claimed it was "yardyard yard".

We did an experiment in my societies and culture class where we tested translations between several different languages using several different services. What's really interesting to see is when you translate between a language and back again, or go through multiple channels to origin--eg, English->French->German->English. We still have a long way to go before machines can provide perfect translations, but that's part of the fun right? Pushing the boundaries and finding new inventive ways to solve the problem of allowing anyone in the world to communicate with anyone else by bringing down the language barrier. We're closer today than we've ever been, and we'll be closer tomorrow, and so on.