Terminology Extraction and Ontology Construction for Semitic Languages Applied to a Specific Domain

Abstract:

The Semitic family includes many languages and dialects spoken by a large number of native speakers (around 300 million). However, Semitic languages as a whole are still understudied. The most prominent members of this family are Arabic (and its dialects), Hebrew, Amharic, Aramaic, Maltese and Syriac. In this article, we are interested in developing a multilingual ontology for a set of languages including Semitic languages. We start by applying Arabic and its dialects in this preliminary research and possibly considering other languages such as Amazigh, a language spoken by North Africans and some immigrants in some parts of Europe. Amazigh language has its own dialects to consider lately in this research. An ontology is the knowledge of a domain represented in a declarative form that provides vocabularies about the different concepts within this domain and their relationships. The transformation of the Arabic WordNet to Ontology and translation with/from other ontologies become the cornerstone technology in many domains where decision makers of specific domain can interpret data and its meaning to establish a common operational picture among the domain.

nsdlogo2016