Salamu Alaykum Hasan, Firstly, allow me welcome you to the Quranic Arabic Corpus project and point you to the comp-quran mailing list archive: http://www.mail-archive.com/comp-qu...@comp.leeds.ac.uk. Your questions are already answered there - but I would be happy to cover this again for you.
1) JQuranTree was a project initiated before the Quranic Arabic Corpus annotation effort began. Hence, although it gives access to orthographic information, it doesn't cover any of the recent annotation added to the corpus. However, as you are enquiring about a Java API I would assume that you are therefore computer-savvy. Most researchers use the published datasets, which you can download from this page: http://corpus.quran.com/download. For morphology, you can download a flat file (1 line per word in the Quran) which contain morphological tags. You can parse this file to pull out the tags you are interested in (e.g. part-of-speech, lemma, root, etc). The format of the tags are documented on the Quranic Arabic Corpus website ( http://corpus.quran.com/documentation/morphologicalfeatures.jsp) 2) I am afraid that since the syntactic treebank is still a work in progress, with 11,000 words completed out of a total of 77,430 words in the Quran. As such, we haven't released any data files or tools related to this yet. As soon as the treebank is completed we will be sure to announce it's availability for download. I hope that helps answer your questions. If you are interested in anything else, please let me know, I would be happy to help. Kind Regards, -- Kais Dukes Language Research Group School of Computing, University of Leeds http://corpus.quran.com - The Quranic Arabic Corpus http://www.kaisdukes.com - Kais Dukes ------------------------------------------------------------- From: Hassan Rom[SMTP:putera.afa...@gmail.com<smtp%3aputera.afa...@gmail.com> ] Sent: Thursday, May 13, 2010 9:03:23 PM To: Kais Dukes Subject: Re: syntactic tree diagrams Auto forwarded by a Rule Assalamu alaikum, Another thing: I noticed that there isn't an API for accessing the part of speech and morphological features data in the current release of jqurantree API. Are there plans to do so? I'd like to do some analysis of the two data. Thanks! - Hassan On Thu, May 13, 2010 at 8:49 PM, Hassan Rom <putera.afa...@gmail.com<mailto: putera.afa...@gmail.com>> wrote: Assalamu alaikum, I am a student of Arabic and I love your syntactic tree diagrams on http://corpus.quran.com! Do you mind sharing with me the library/software you used to generate those diagrams? I'm interested to generate syntactic tree diagrams for the sentences we analyze in our arabic class. Thanks! -- Hassan Rom
