Google Translation of Lorem Ipsum | Hacker News Reader

Google Translation of Lorem Ipsum

translate.google.com

48 pointsskrebbel11 comments

I'm pretty sure this is a result of the way google translate works and the fact that Lorem Ipsum is placeholder text. On a (very) high level google translate looks for groups of text that it knows is translated already and uses all that information to translate large chunks of text for the user. Since Lorem Ipsum is just placeholder text, people use it before they have real content, which results is random text across multiple sites. Google is picking up all those random messages and trying to make the best of it.

I tend to agree. When Latin translation was first introduced by Google in 2010, the first words of "lorem ipsum" then translated to "Hello World!"

I thought it was an Easter egg at the time, as that seems more specific to programming languages - something a developer might deliberately place in there.

It's even more amusing if you go to http://translate.google.com/#la/en/ and start slowly entering Lorem ipsum by hand. Highlights:

  Lorem                                  
     → Product
  Lorem ip                               
     → We recall
  Lorem ips                              
     → IPS News
  Lorem ipsu                             
     → Dummy Item
  Lorem ipsum                            
     → Welcome
  Lorem ipsum do                         
     → We give
  Lorem ipsum dol                        
     → This mourning
  Lorem ipsum dolor                      
     → Welcome
  Lorem ipsum dolor s                    
     → The Pussycat Dolls
  Lorem ipsum dolor si                   
     → Contact if
  Lorem ipsum dolor sit ame              
     → Welcome Home
  Lorem ipsum dolor sit amet             
     → Product Manager
  Lorem ipsum dolor sit amet,            
     → This page is currently
  Lorem ipsum dolor sit amet, c          
     → This page is available
  Lorem ipsum dolor sit amet, consectetur
     → This page is half the battle
  Lorem ipsum dolor sit amet, consectetur adipisicing elit
     → This page is half the battle WIN!

The results are slightly different if you don't capitalize “Lorem”.

Edit: lipsum.com explains the source of the text; it is a slightly garbled fragment of a sentence from de Finibus Bonorum et Malorum by Cicero: “Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem” which translates as “Nor again is there anyone who loves or pursues or desires to obtain pain of itself, because it is pain, but because occasionally circumstances occur in which toil and pain can procure him some great pleasure.”

Lorem Ipsum is not real Latin:

http://en.wikipedia.org/wiki/Lorem_ipsum

Which is why it's funny that it translates :P

I think that google uses a lot of machine learning for translations. From the translation results of lorem ipsum, I think we can conclude that their engine uses websites for training data. Websites that have lots of "under development" texts and mockup buttons, and also lorem ipsum.

It's interesting that the all caps loremipsum site translates differently.

http://translate.google.com/translate?hl=en&sl=la&tl...

Another version from limpsum.com: http://translate.google.com/translate?hl=en&sl=la&tl...

Something strange going on here, some of the English translation is misspelt: ervey, lteter,

Well, and I'm pretty sure Joomla! and Add To Cart don't belong in there either.

Pretty much any web corpus will contain lots of this text, alongside lots of other random things, so statistical translation will produce... this.

It is the usual quality of translation that is produced by google.

Reply on news.ycombinator.com