Semantic composition process in a speech understanding system

Frédéric Duvert (1) , Marie-Jean Meurs (1) , Christophe Servan (1) , Frédéric Béchet (1) , Fabrice Lefèvre (1) , Renato de Mori (1)

1 LIA - Laboratoire Informatique d'Avignon

A knowledge representation formalism for SLU is introduced. It is used for incremental and partially automated annotation of the MEDIA corpus in terms of semantic structures. An automatic interpretation process is described for composing semantic structures from basic semantic constituents using patterns involving constituents and words. The process has procedures for obtaining semantic compositions and for generating frame hypotheses by inference. This process is evaluated on a dialogue corpus manually annotated at the word and semantic constituent levels.

Mots clés: Spoken language understanding; semantic structures; frames; conceptual decoding; semantic annotation; semantic inference

Domaines: Traitement du texte et du document

Frédéric Duvert, Marie-Jean Meurs, Christophe Servan, Frédéric Béchet, Fabrice Lefèvre, et al.. Semantic composition process in a speech understanding system. The 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Mar 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4518788⟩. ⟨hal-01158578⟩