AR2B: FORMALIZATION OF ARABIC TEXTS WITH EVENT-B

• Main Authors: Kheira-Zineb Bousmaha Ossoukine, Lamia Belguith Hadrich
• Format: Article
• Language: English
• Published: Scientific Research Support Fund of Jordan (SRSF) and Princess Sumaya University for Technology (PSUT) 2020-06-01
• Series: Jordanian Journal of Computers and Information Technology
• Subjects: arabic natural language processing; information system; information extraction; formals’ specification; event-b
• Online Access: https://jjcit.org/paper/85

Transforming natural software requirements into a more formal specification is difficult and may be an excellent application for natural language processing. This problem is not recent. It aroused and still arouses great interest, because it gives rise to many challenges in various scientific fields, such as automatic language processing, requirements engineering, knowledge representation and formal verification. This paper proposes a platform and a strategy to transform software requirements specified to formal specification with event-B. The texts used are those of Arabic language, which is really a challenge. The Ar2B system is built and the experiments showed good results with an accuracy of 70%.