Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

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.




Consider applying for YC's Winter 2027 batch! Applications are open till November 2.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: