Mobile menu

Using language identifier websites/"language guessing software"?
Thread poster: Jan Sundström

Jan Sundström  Identity Verified
Sweden
Local time: 00:43
English to Swedish
+ ...
Nov 2, 2007

Hi all,

I sometimes receive source documents where neither me nor the clients knows which language it's written in.

From another thread, I got some recommendations on language identification software.

Did any of you try these resources?
http://www.polyglot3000.com/'

http://www.xrce.xerox.com/competencies/content-analysis/tools/guesser-ISO-8859-1.en.html
http://complingone.georgetown.edu/~langid/
http://www.appliedlanguage.com/language_identifier.shtml
http://www.lextek.com/langid/li/onlineidentifier.html

What experiences do you have? How accurate are they?

If you try to enter a lesser known language, or a non-western alphabet, which of the sites above are successful in guessing?!

Thanks a lot for your input,

Jan

[Edited at 2007-11-02 15:33]


Direct link Reply with quote
 

Henry Hinds  Identity Verified
United States
Local time: 16:43
English to Spanish
+ ...
But what good is that? Nov 2, 2007

Surely you cannot translate it if you do not even know what language it is. And if you have an agency and a "stable" of translators, you should be able to identify the language even though you do not know it, from your knowledge of what their working languages are.

Of course as a matter of curiosity it is something else.


Direct link Reply with quote
 

Jan Sundström  Identity Verified
Sweden
Local time: 00:43
English to Swedish
+ ...
TOPIC STARTER
Explanation Nov 4, 2007

Hi Henry,

That's exactly the scenario I mean:

If I can't translate it myself, I have to outsource the translation to a fellow freelancer.
And being a Proz member, what better than to match the job with the right guy, after searching in the Freelancers Directory!

So this is when I'll need to use the language guessing software.

Now, does anyone else have any recommendations or experience in this field?!

/Jan


Direct link Reply with quote
 

Samuel Murray  Identity Verified
Netherlands
Local time: 00:43
Member (2006)
English to Afrikaans
+ ...
Two uses Nov 5, 2007



Isn't this just the Xerox one?



Freeware for non-commercial purposes. Does 260 languages, installs nicely (2.1 MB download).

Such programs are nice for:

* When a potential client thinks that I can do that language, I can redirect him to a translator who might be able to.
* When I get information that needs to be MT'ed (eg when I do reference searches in Google) and I don't know what language it is written in.


[Edited at 2007-11-05 08:13]


Direct link Reply with quote
 

Jan Sundström  Identity Verified
Sweden
Local time: 00:43
English to Swedish
+ ...
TOPIC STARTER
Thanks! Nov 12, 2007

Samuel Murray wrote:



Isn't this just the Xerox one?


I guess you're right, Sam!
BTW, good idea to MT search results that you can't identify. That's another good usage for this software.

/Jan


Direct link Reply with quote
 

Jan Sundström  Identity Verified
Sweden
Local time: 00:43
English to Swedish
+ ...
TOPIC STARTER
More links Feb 14, 2008



Hi again,

I found a few more links to tools, but I haven't had time to test them yet:
http://odur.let.rug.nl/~vannoord/TextCat/Demo/textcat.html
http://tandibusiness.blogspot.com/2008/02/language-identifiers-and-language.html

(Scroll down for link lists...)

/Jan


Direct link Reply with quote
 


To report site rules violations or get help, contact a site moderator:


You can also contact site staff by submitting a support request »

Using language identifier websites/"language guessing software"?

Advanced search






Déjà Vu X3
Try it, Love it

Find out why Déjà Vu is today the most flexible, customizable and user-friendly tool on the market. See the brand new features in action: *Completely redesigned user interface *Live Preview *Inline spell checking *Inline

More info »
Across v6.3
Translation Toolkit and Sales Potential under One Roof

Apart from features that enable you to translate more efficiently, the new Across Translator Edition v6.3 comprises your crossMarket membership. The new online network for Across users assists you in exploring new sales potential and generating revenue.

More info »



All of ProZ.com
  • All of ProZ.com
  • Term search
  • Jobs