Arabic-L:LING:Automatically parsing an Arabic Corpus

[Dilworth Parkinson]

------------------------------------------------------------------------
Arabic-L: Sat 08 Aug 2009
Moderator: Dilworth Parkinson <dilworth_parkinson at byu.edu>
[To post messages to the list, send them to arabic-l at byu.edu]
[To unsubscribe, send message from same address you subscribed from to
listserv at byu.edu with first line reading:
             unsubscribe arabic-l                                      ]

-------------------------Directory------------------------------------

1) Subject:Automatically parsing an Arabic Corpus

-------------------------Messages-----------------------------------
1)
Date: 08 Aug 2009
From:Kais Dukes <kais.dukes at jqurantree.org>
Subject:Automatically parsing an Arabic Corpus

Hello,

There is currently an accurate (in progress) part-of-speech tagged  
Arabic
corpus available (http://quran.uk.net). I want to now produce a  
syntactic
parse of this corpus automatically. I understand that there are several
parsers I could use, e.g. MaltParser for dependences, or the Collins/  
Bikel
parser for constituent phrase structure trees.

My question is, is there a pre-trained publicly available parser for  
Arabic?
Given that the resulting corpus is to be fully open source / public  
domain,
I'm really looking for a publically available parser. I would like to  
parse
the Arabic text of the Quran corpus, given that it already has
part-of-speech tags.

So far, I've found the Standford parser:
http://nlp.stanford.edu/software/parser-arabic-faq.shtml

Any help on other pre-trained parsers would be greatly appreciated!

Kind Regards,

-- Kais Dukes
dukes.kais at gmail.com



--------------------------------------------------------------------------
End of Arabic-L:  108 Aug 2009


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/arabic-l/attachments/20090808/69e30a93/attachment.htm>