8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


How NLP Techniques can Improve Speech Understanding: ROMUS - A Robust Chunk Based Message Understanding System Using Link Grammars

Jerome Goulian, Jean-Yves Antoine, Franck Poirier

University of South-Brittany, France

This paper discusses the issue of how a speech understanding system can be made robust against spontaneous speech phenomena (hesitations and repairs) as well as achieving a detailed analysis of spoken French. The Romus system is presented. It implements speech understanding in a two-stage process. The first stage achieves a finite-state shallow parsing that consists in segmenting the recognized sentence into basic units (spoken-adapted chunks). The second one, a Link Grammar parser, looks for inter-chunks dependencies in order to build a rich representation of the semantic structure of the utterance. These dependencies are mainly investigated at a pragmatic level through the consideration of a task concept hierarchy. Discussion about the approach adopted, its benefits and limitations, is based on the results of the system's assessment carried out under different linguistic phenomena during an evaluation campaign held by the French CNRS.

Full Paper

Bibliographic reference.  Goulian, Jerome / Antoine, Jean-Yves / Poirier, Franck (2003): "How NLP techniques can improve speech understanding: ROMUS - a robust chunk based message understanding system using link grammars", In EUROSPEECH-2003, 2773-2776.