المستخلص: |
A completely tagged corpus of Arabic can form the basis for different research activities. First of all it is a suitable instrument for pure linguistic research, but it can also become an interesting tool for computer applications varying from Machine Translation, or the spell check of scanned documents, to the automatic tagging of raw corpora and also form the basis for the development of CALL applications. In this paper we discuss the lexical database that we have developed at the University of Leuven, as well as the first tools that have been developed to perform POS -tagging of Arabic corpora.
|