الاسترجاع الآلي للصيغ الصرفية من المعجم الوسيط الإلكتروني

الملخص EN

The digitization of the corpora of the Arabic language is the beginning of the "thesaurus" project, as well as the Arabic "historical lexicon" project.

This digitization makes it possible to apply certain automatic processing procedures to real linguistic samples such as: automatic search, information retrieval, etc.

.

.

.

As far as we are concerned, we have adopted as a digital corpus the lexicon "Al muajem Al Wassit " conceived by a team from the Arabic Academy of Cairo, in its fourth edition, and we tried to apply an automatic search mechanism in all the lexical entries of the different schemes (morphological forms) derived from the trilitary mujarrad verbs, as well as the lexical definition that follows.

We have encountered several difficulties, some of which relate to the digitization of our adopted lexicon (Al Muajem Al Wassit), others relate to the features of the Arabic language, and finally, others relate to the obsolete lexicographical techniques of this lexicon.

For these reasons, we had to filter the results obtained after each automatic extraction of a scheme from the electronic version of our lexicon.

Our conclusion is an appeal to all actors in the lexicological and lexicographical field of the Arabic language, to question their techniques and methodology of corpora digitization of the Arabic language.