Morphological Analysis of Classical and Modern Standard Arabic Text التحليل الصَّرفي لنصوص اللغة العربية الحديثة والكلاسيكية
Atwell, ES and Sawalha, M
(2011)
Morphological Analysis of Classical and Modern Standard Arabic Text التحليل الصَّرفي لنصوص اللغة العربية الحديثة والكلاسيكية.
In:
Proceedings of the 7th International Computing Conference in Arabic (ICCA11).
7th International Computing Conference in Arabic (ICCA11), 31 May - 02 Jun 2011, Imam Mohammed Ibn Saud University, Riyadh, KSA.
The University of Leeds
.
Abstract
This paper shows the details of empirical study of applying standards and tools for Arabic morphological analysis, in addition to linguistic information extracted from long established traditional Arabic grammar books, to reuse and enriching existing resources with fine-grain morphological features in formation. SALMA Tag Set is used as standard in this work. And the tool used in this study is the SALMA Tagger [2, 3]. The reuse of existing components is an established principle in software engineering. We used the Quranic Arabic Corpus morphological annotation of a test text sample of chapter 29, consisting of about 1000 words. Then, an automated mapping methodology mapped the QAC morphological tags to SALMA morphological features tags. The mapping between the QAC morphological tags and SALMA morphological features tags is done by following five steps procedure. This result proves that the reuse and enriching of existing resource with more detailed morphological features information is applicable and can provide a tagged corpora of fine grain analysis.
Metadata
Authors/Creators:
Atwell, ES
Sawalha, M
Copyright, Publisher and Additional Information:
Atwell, ES and Sawalha, M (c) 2011, University of Leeds. Reproduced with permission from the copyright holders.
Keywords:
Morphological analysis; Arabic language; The holy Qur’an; Reuse; SALMA - Tag Set; Gold standard for evaluating morphological analyzers of Arabic text
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)