[Corpora-List] Automatically parsing an Arabic Corpus

[Kais Dukes]

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 Stanford 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





_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora