[Corpora-List] ocr for corpus in arabic transcription needed

Ghassan Mourad Ghassan.Mourad at paris4.sorbonne.fr
Fri Dec 20 11:32:49 UTC 2002


bonjour, 

you can look in this site : www.sakhar.com/sakhar_e/ 
> 
>for arabic NLP


Hello 
>> 
>> I am trying to establish a corpus of Arabic text using the latin 
>> transcription alphabet for Arabic. I have had trouble finding an optical 
>> character recognition program which can recognize the special characters 
>of 
>> the transcription alphabet (which are not part of the alphabet of any 
>> language) as letters in order to create a word document or rich text 
>formate 
>> file. Can you recommend an OCR? 
>> 
>> Thank you very much. 
>> H. Schaufelberger. 
>>



----------
Ghassan Mourad
Paris - Sorbonne
ISHA 
Equipe LaLICC (Langage, Logique, Informatique, Cognition et Communication) 
http://www.lalic.paris4.sorbonne.fr/
96, Bd Raspail
75006 Paris
France 
tél : 01 44 39 35 90
fax : 01 44 39 35 91 



More information about the Corpora mailing list