I.J. Intelligent Systems and Applications, 2017, 8, 11-24 Published Online August 2017 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijisa.2017.08.02 Copyright © 2017 MECS I.J. Intelligent Systems and Applications, 2017, 8, 11-24 Parsing Arabic Nominal Sentences Using Context Free Grammar and Fundamental Rules of Classical Grammar Nabil Ababou and Azzeddine Mazroui University Mohammed First, Faculty of Sciences, Oujda, Morocco E-mail: nabilaababou@gmail.com, azze.mazroui@gmail.com Rachid Belehbib University Mohammed First, Faculty of Arts and Humanities, Oujda, Morocco E-mail: racbel59@hotmail.com Received: 06 March 2017; Accepted: 06 July 2017; Published: 08 August 2017 Abstract—This work falls within the framework of the Arabic natural language processing. We are interested in parsing Arabic texts. Existing parsers generate parse trees that give an idea about the structure of the sentence without considering the syntactic functions specific to the Arabic language. Thus, the results are still insufficient in terms of syntactic information. The system we have developed in this article takes into consideration all these syntactic functions. This system begins with a morphological analysis in the context. Then, it uses a CFG grammar to extract the phrases and ends by exploiting the formalism of unification grammar and traditional grammar to combine these phrases and generate the final sentence structure. Index Terms—POS tagger, Parser, Arabic phrase, grammar, syntax tree, syntactic functions. I. INTRODUCTION Parsing is a fundamental step to the design of several applications in Arabic natural language processing such as spelling and grammar checker, information retrieval, automatic generation of sentences, machine translation, conversion information system and Querying Database [1,2]. Parsing a sentence is usually a tricky task. It is more complex with languages whose morphology and syntax is very rich, as in the case of the Arabic language. This explains the challenges that face the development of automatic systems allowing to carry out a syntactic analysis. Arabic parsers have been reported in [3,4] All these initiatives use grammars created manually. Recently, Arabic Treebank (ATB) was used to improve the performance of the syntactic analysis since it covers widely the Arabic language [5]. Similarly, approaches based on statistical treatment have been developed [6]. However, these analyzers have adopted techniques used for English and do not take into account the specificities of the Arabic language. Thus, if we consider the outputs of the Stanford parser 1 related to the analysis of the four simple sentences of Table 1, we notice that we have no information about the subject (جزذأ اى\Almbtd> 2 \) or the predicate ( اىخجش\Alxbr\) of the first two sentences of the table. The analyzer does not distinguish between the words ذا عؼ\sEdA\ (happy) and  قبد\qdm\ (coming), while they play two different syntactic roles: predicate for the first and circumstantial phrase ( اىحبه\AlHAl\) for the second. For the last two examples, the system generates the same tree consisting of a single phrase despite the difference between them. Indeed, the third example is a complete sentence composed of two phrases that are the subject ىذ اى\Alwld\ (the boy) and the predicate جزغ \mbtsm\ (smiling), while the last example is not a complete sentence but only a phrase composed of a noun ىذ اىand its adjective جزغ اى \Almbtsm\ (the smiling). Table 1. Result the analysis of four examples by the Stanford parser N Sentence Result 1 ذا عؼىذ قبد اى \Alwld qAdm sEydA\ (The boy is coming happy) (ROOT (S (NP (DTNN ىذاى)) (ADJP (JJ قبد) (JJ ذاعؼ)))) 2 ىذ اىذا عؼ قبد \Alwld sEydA qAdm \ (The boy is coming happy) (ROOT (S (NP (DTNN ىذاى)) (ADJP (JJ ذاعؼ) (JJ قبد)))) 3 ىذ اىجزغ \Alwld mbtsm\ (The boy is smiling) (ROOT (NP (DTNN ىذاى) (DTJJ جزغ))) 4 جزغىذ اى اى \Alwld Almbts\ (The smiling boy) (ROOT (NP (DTNN ىذاى) (DTJJ جزغاى))) Unlike the other parsers, which have adopted annotations derived from those introduced by English 1 https://nlp.stanford.edu/software/lex-parser.html 2 Buckwalter transliteration http://www.qamus.org/transliteration.htm