In this paper, we present two methods for correcting Arabic words generated by text and/or speech recognizers. These techniques operate as post-processors and they are conceived to be adaptable. They correct rejection and substitution word errors. The former one is very linked to the dictionary and is called 'lexicon driven', when the orther is very general exploiting contextual information and called 'context driven'. Arabic language properties are very useful in morpho-lexical analysis and so they were strongly exploited in the development of the second method. Substitution errors are rewritten in rules for being used by a rule based system. The extensions to the other levels of language analysis are considered in perspectives.
A graph circuit is a planar graph in which edges are oriented such that any finite face is a circuit. Such graph is said to be minimum if the number of edges oriented in two direction is minimum. In this article we study such graph properties. We prove that each finite face can be characterized by its orientation direction. We also present sum results on the disposition of edges oriented in two directions in a minimum graph circuit.
