Parsing strategy for spoken language interfaces with a lexicalized tree grammar

Our work addresses the integration of speech recognition and natural language processing for spoken dialogue systems. To deal with recognition errors, we investigate two repairing strategies integrated in a parsing based on a Lexicalized Tree Grammar. The rst strategy takes its root in the recognition hypothesis, the other in the linguistic expectations. We expose a formal framework to express the grammar, to describe the repairing strategies and to foresee further strategies.