<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><pre id="nonprop"><p align=""><font class="Apple-style-span" face="Helvetica" size="3"><span class="Apple-style-span" style="font-size: 12px; ">------------------------------------------------------------------------
Arabic-L: Sat 08 Aug 2009
Moderator: Dilworth Parkinson <<a href="mailto:dilworth_parkinson@byu.edu">dilworth_parkinson@byu.edu</a>>
[To post messages to the list, send them to <a href="mailto:arabic-l@byu.edu">arabic-l@byu.edu</a>]
[To unsubscribe, send message from same address you subscribed from to
<a href="mailto:listserv@byu.edu">listserv@byu.edu</a> with first line reading:
            unsubscribe arabic-l                                      ]

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

1) Subject:Automatically parsing an Arabic Corpus

-------------------------Messages-----------------------------------
1)
Date: 08 Aug 2009
From:<span class="Apple-style-span" style="font-size: medium; white-space: normal; ">Kais Dukes <<a href="mailto:kais.dukes@jqurantree.org">kais.dukes@jqurantree.org</a>></span>
Subject:Automatically parsing an Arabic Corpus

<span class="Apple-style-span" style="font-size: medium; white-space: normal; ">Hello,<br><br>There is currently an accurate (in progress) part-of-speech tagged Arabic<br>corpus available (<a href="http://quran.uk.net/">http://quran.uk.net</a>). I want to now produce a syntactic<br>parse of this corpus automatically. I understand that there are several<br>parsers I could use, e.g. MaltParser for dependences, or the Collins/ Bikel<br>parser for constituent phrase structure trees.<br><br>My question is, is there a pre-trained publicly available parser for Arabic?<br>Given that the resulting corpus is to be fully open source / public domain,<br>I'm really looking for a publically available parser. I would like to parse<br>the Arabic text of the Quran corpus, given that it already has<br>part-of-speech tags.<br><br>So far, I've found the Standford parser:<br><a href="http://nlp.stanford.edu/software/parser-arabic-faq.shtml">http://nlp.stanford.edu/software/parser-arabic-faq.shtml</a><br><br>Any help on other pre-trained parsers would be greatly appreciated!<br><br>Kind Regards,<br><br>-- Kais Dukes<br><a href="mailto:dukes.kais@gmail.com">dukes.kais@gmail.com</a><br></span><br></span></font></p><p align=""><font class="Apple-style-span" face="Helvetica" size="3"><span class="Apple-style-span" style="font-size: 12px; ">
--------------------------------------------------------------------------
End of Arabic-L:  108 Aug 2009
</span></font></p><div><font class="Apple-style-span" face="Helvetica" size="3"><span class="Apple-style-span" style="font-size: 12px;"><br></span></font></div></pre></body></html>