recongizing language

Thread view:

Andrius Klimavi?ius - 01 Jul 2005 09:35 GMT

Helo,

i have a task to recognize two languages: English and Lithuanian.
First thing, i think, is to search for specific letters, also for
words such like: are, to, into, the etc. Am i going the right way?:)

any ideas how to do that?

Reply to this Message

Gordon Beaton - 01 Jul 2005 10:33 GMT

> First thing, i think, is to search for specific letters, also for
> words such like: are, to, into, the etc. Am i going the right way?:)
>
> any ideas how to do that?

Yes, I believe that searching for "stop words" in each of the
languages is a simple and reasonably accurate method.

This kind of problem is often discussed in comp.ai.nat-lang, so you
might want to ask there too.

There are various lists of stop words available on the web,
such as this one: http://meta.wikimedia.org/wiki/Stop_word_list

/gordon

Signature

[ do not email me copies of your followups ]
g o r d o n + n e w s @ b a l d e r 1 3 . s e

Reply to this Message

Andrius Klimavi?ius - 04 Jul 2005 12:28 GMT

thnx Gordon:)

Reply to this Message

Free Magazines

Get these publications absolutely FREE for up to 12 months. There are no hidden fees and no obligation. Simply choose a title, complete the application form and submit it. Read more ...