CONSTRAINT-BASED AND FUZZY LOGIC STUDENT MODELING FOR ARABIC GRAMMAR نمذجة الطالب القائم على المنطق الضبابي لقواعد اللغة العربية CONSTRAINT-BASED AND FUZZY LOGIC STUDENT MODELING FOR ARABIC GRAMMAR CONSTRAINT-BASED AND FUZZY LOGIC STUDENT MODELING FOR ARABIC GRAMMAR CONSTRAINT-BASED AND FUZZY LOGIC STUDENT MODELING FOR ARABIC GRAMMAR

Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with linguistic skills. Adding intelligence in such systems is mainly based on using Natural Language Processing (NLP) tools to diagnose student errors, especially in language grammar. However, most such systems do not consider the modeling of student competence in linguistic skills, especially for the Arabic language. In this paper, we will deal with basic grammar concepts of the Arabic language taught for the fourth grade of the elementary school in Egypt. This is through Arabic Grammar Trainer (AGTrainer) which is an Intelligent CALL. The implemented system (AGTrainer) trains the students through different questions that deal with the different concepts and have different difficulty levels. Constraint-based student modeling (CBSM) technique is used as a short-term student model. CBSM is used to define in small grain level the different grammar skills through the defined skill structures. The main contribution of this paper is the hierarchal representation of the system's basic grammar skills as domain knowledge. That representation is used as a mechanism for efficiently checking constraints to model the student knowledge and diagnose the student errors and identify their cause. In addition, satisfying constraints and the number of trails the student takes for answering each question and fuzzy logic decision system are used to determine the student learning level for each lesson as a long-term model. The results of the evaluation showed the system's effectiveness in learning in addition to the satisfaction of students and teachers with its features and abilities. تعلم اللغة بمساعدة الكمبيوتر (CALL) هي أنظمة تعليمية تعتمد على الكمبيوتر وتتعامل مع المهارات اللغوية. تعتمد إضافة الذكاء في مثل هذه الأنظمة بشكل أساسي على استخدام أدوات معالجة اللغة الطبيعية (NLP) لتشخيص أخطاء الطلاب، خاصة في قواعد اللغة. ومع ذلك، فإن معظم هذه الأنظمة لا تأخذ في الاعتبار نمذجة كفاءة الطالب في المهارات اللغوية، خاصة بالنسبة للغة العربية. سنتناول في هذه الورقة المفاهيم النحوية الأساسية للغة العربية التي تدرس للصف الرابع الابتدائي في مصر. وذلك من خلال المدرب النحوي العربي (AGTrainer) وهو عبارة عن مكالمة ذكية. يقوم النظام المطبق (AGTrainer) بتدريب الطلاب من خلال أسئلة مختلفة تتعامل مع المفاهيم المختلفة ولها مستويات صعوبة مختلفة. تُستخدم تقنية النمذجة الطلابية القائمة على القيود (CBSM) كنموذج طلابي قصير الأجل. يتم استخدام CBSM لتحديد المهارات النحوية المختلفة في مستوى الحبيبات الصغيرة من خلال هياكل المهارات المحددة. تتمثل المساهمة الرئيسية لهذه الورقة في التمثيل الهرمي للمهارات النحوية الأساسية للنظام كمعرفة بالمجال. يتم استخدام هذا التمثيل كآلية للتحقق بكفاءة من القيود لنمذجة معرفة الطالب وتشخيص أخطاء الطالب وتحديد أسبابها. بالإضافة إلى ذلك، يتم استخدام القيود المرضية وعدد المسارات التي يأخذها الطالب للإجابة على كل سؤال ونظام قرار منطقي غامض لتحديد مستوى تعلم الطالب لكل درس كنموذج طويل الأجل. أظهرت نتائج التقييم فعالية النظام في التعلم بالإضافة إلى رضا الطلاب والمعلمين بميزاته وقدراته. Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with linguistic skills. Adding intelligence in such systems is mainly based on using Natural Language Processing (NLP) tools to diagnose student errors, especially in language grammar. However, most such systems do not consider the modeling of student competence in linguistic skills, especially for the Arabic language. In this paper, we will deal with basic grammar concepts of the Arabic language taught for the fourth grade of the elementary school in Egypt. This is through Arabic Grammar Trainer (AGTrainer) which is an Intelligent CALL. The implemented system (AGTrainer) trains the students through different questions that deal with the different concepts and have different difficulty levels. Constraint-based student modeling (CBSM) technique is used as a short-term student model. CBSM is used to define in small grain level the different grammar skills through the defined skill structures. The main contribution of this paper is the hierarchical representation of the system's basic grammar skills as domain knowledge. That representation is used as a mechanism for efficiently checking constraints to model the student knowledge and diagnose the student errors and identify their cause. In addition, satisfying constraints and the number of trails the student takes for answering each question and fuzzy logic decision system are used to determine the student learning level for each lesson as a long-term model. The results of the evaluation showed the system's effectiveness in learning in addition to the satisfaction of students and teachers with its features and abilities. L'apprentissage assisté par ordinateur (CALL) est un système de tutorat informatisé qui offre des compétences linguistiques. Adding intelligence in such systems is mainly based on using Natural Language Processing (NLP) tools to diagnose student errors, especially in language grammar. However, most such systems do not consider the modeling of student competence in linguistic skills, especially for the Arabic language. In this paper, we will deal with basic grammar concepts of the Arabic language taught for the fourth grade of the elementary school in Egypt. This is through Arabic Grammar Trainer (AGTrainer) which is an Intelligent CALL. The implemented system (AGTrainer) trains the students through different questions that deal with the different concepts and have different problemulty levels. La technique CBSM (Constraint-based student modeling) est utilisée comme modèle étudiant à court terme. Le CBSM est utilisé pour définir dans les petits niveaux de grammaire les différentes compétences grammaticales à travers les structures de compétences définies. La principale contribution de ce document est la représentation hiérarchique des compétences grammaticales de base du système en tant que connaissance du domaine. That representation is used as a mechanism for efficiently checking constraints to model the student knowledge and diagnose the student errors and identify their cause. In addition, satisfying constraints and the number of trails the student takes for answering each question and fuzzy logic decision system are used to determine the student learning level for each lesson as a long-term model. Les résultats de l'évaluation ont porté atteinte à l'efficacité du système en matière d'apprentissage, en plus de la satisfaction des étudiants et des enseignants avec ses caractéristiques et ses capacités. Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with linguistic skills. Adding intelligence in such systems is mainly based on using Natural Language Processing (NLP) tools to diagnose student errors, especially in language grammar. However, most such systems do not considers the modeling of student competence in linguistic skills, especially for the Arabic language. In this paper, we will deal with basic grammar concepts of the Arabic language taught for the fourth grade of the elementary school in Egypt. This is through Arabic Grammar Trainer (AGTrainer) which is an Intelligent CALL. The implemented system (AGTrainer) trains the students through different questions that deal with the different concepts and have different difficulty levels. La técnica de modelado de estudiantes basado en restricciones (CBSM) se utiliza como modelo de estudiante a corto plazo. CBSM se utiliza para definir en pequeños niveles de grano las diferentes habilidades gramaticales a través de las estructuras de habilidades definidas. The main contribution of this paper is the hierarchal representation of the system 's basic grammar skills as domain knowledge. That representation is used as a mechanism for efficiently checking constraints to model the student knowledge and diagnose the student errors and identify their cause. Además, las restricciones de satisfacción y el número de pistas que el estudiante toma para responder a cada pregunta y el sistema de decisión lógica difusa se utilizan para determinar el nivel de aprendizaje del estudiante para cada lección como un modelo a largo plazo. The results of the evaluation showed the system 's effectiveness in learning in addition to the satisfaction of students and teachers with its features and abilities.