An interesting Google Translate quirk | Hacker News Reader

An interesting Google Translate quirk

translate.google.com

21 pointsDavidSJ14 comments

Is this a quirk of statistical machine translation where the word English shows up in English texts where Francais would show up in French texts?

It's a lesson in the difference between translation and localization.

In this case, Google's approach confuses the latter for the former, because its corpus contains parallel texts that have not only been translated (into a different language), but also localized (into a different locale). For example, it may be extrapolating incorrectly from a French document and an English document with the following phrases in the same location:

  FR Cliquez ici pour la version anglaise.
  EN Click here for the French version.

This sign is another good example of how parallel texts are not always translations:

http://flickr.com/photos/jadelin/2205088201/

(the Japanese "おかえりなさい" here means "Welcome home")

In your Japanese airport example I think they're intentionally not the same phrase. "Welcome back" to the Japanese people and "Welcome to Japan" to the foreigners.

Yes, that is why it's not a translation, but a localization (you know, for the locals).

Gotcha.

Now remove the period at the end of the URL. :)

Interestingly, if you remove "ensemble", then it reverses it.

So:

"Nous parlons français ensemble." -> "We speak English together."

"Nous parlons français ensemble" -> "We all speak French"

"Nous parlons français." -> "We speak French."

"Nous parlons français" -> "We speak English"

Also, it is language dependant, in German we speak French together:

Wir sprechen französisch zusammen

Ive had this with Swedish as well.

Jag kan inte prata svenska

turns into:

I can't speak English

Nice. It looks like it's confusing the different meanings of "English": "a language originating in England" vs. "native tongue".

If you're translating something like "Give it to me in plain English", you'd want the second meaning. Likewise, "It's Greek to me" doesn't hold the quite same weight when translated literally into Greek.

Could be. If you tell it to translate to Spanish, it says "Inglés" (which is incorrect, btw, since it shouldn't be capitalized) or "francés", depending on whether you leave the period. But, if you tell it to translate into German, it says "französisch" either way.

Yeap. In Greek we say 'It's chinese to me'. I wonder what the chinese say :)

Good question. After a bit of searching, I found these nation / translation tables. Neat!

  * http://www.omniglot.com/language/idioms/incomprehensible.php
  * http://www.nationmaster.com/encyclopedia/Greek-to-me

HAH

it's a conSPIRACY!

Reply on news.ycombinator.com