Robust analysis of spoken input combining statistical and knowledge-based information sources

The work presented in this paper concerns the analysis of automatic transcription of spoken input into an interlingua formalism for a speech-to-speech machine translation system. This process is based on two sub-tasks, (1) the recognition of the Domain Action (a speech act and a sequence of concepts) and (2) the extraction of arguments consisting of feature-value information. Statistical models are used for the former, while a knowledge-based approach is employed for the latter. This paper proposes an algorithms that improves the analysis in terms of robustness and performance: it combines the scores of the statistical models with the extracted arguments, taking in account the well-formedness constraints defined by the interlingua formalism.