Which rules for the robust parsing of spoken utterances with Lexicalized ' Iree Adjoining Gramn 1 ars ?

In the context of spoken dialogue systems, we investigated a bottom-up robust parsing for LTAG (Lexicalized Tree Adjoining Grammars) that interleaves a syntactic and a semantic structure. When the regular syntactic composition rules fail, the syntactic islands and the corresponding partial semantic structures are combined thanks to additional local rules. We supply some descriptive limits of the grammar with these rules which depend on the immediate syntactic context of the islands. In this paper, we focus on their application to few spoken phenomena.