Extracting Entities and Relationships from Arabic Text for Information System
Belkacem Kouninef, Badr Al-Johar · 2011
This paper addresses the problem of the development of Arabic Natural Language Interface for Information System Design. Most Arabic systems focus on processing Arabic text for machine translation or information retrieval. We present in this paper some aspects for identify Entities and Relationships from a description of the application domain given with a subset of the Arabic Natural Language. The tool starts, in a first step with an interpretation of Arabic text through the system’s components (morphological, syntax, semantic analyzers) and generates the meaning representation in a first order logic form. Then in the second step, it uses entities rules and relationships rules for extracting Entities and Relationships, which describes the elements of the Conceptual Schema.