This paper describes the development of an intelligent computer-assisted language learning (ICALL) system for learning Arabic. This system could be used for learning Arabic by students at primary schools or by learners of Arabic as a second or foreign language. It explores the use of Natural Language Processing (NLP) techniques for learning Arabic. The learners are encouraged to produce sentences freely in various situations and contexts and guided to recognise by themselves the erroneous or inappropriate functions of their misused expressions. In this system, we use NLP tools (including morphological analyser and syntax analyser) and error analyser to issue feedback to the learner. Furthermore, we propose a mechanism of correction by the learner which allows the learner to correct the typed sentence independently, and allows the learner to realise that what the error is.