论文信息 - A Model for Robust Processing of Spontaneous Speech by Integrating Viable Fragments

A Model for Robust Processing of Spontaneous Speech by Integrating Viable Fragments

We describe the design and function of a robust processing component which is being developed for the Verbmobil speech translation system. Its task consists of collecting partial analyses of an input utterance produced by three parsers and attempting to combine them into more meaningful, larger units. It is used as a fallback mechanism in cases where no complete analysis spanning the whole input can be achieved, owing to spontaneous speech phenomena or speech recognition errors.

Karsten L. Worm

[1] Johan Bos,et al. Managing Information at Linguistic Interfaces , 1998, ACL.

[2] Karsten L. Worm. A Model for Robust Processing of Spontaneous Speech by Integrating Viable Fragments , COLING.

[3] Tomek Strzalkowski,et al. From Discourse to Logic , 1991 .

[4] Johan Bos,et al. Compositional Semantics in Verbmobil , 1996, COLING.

[5] Martin C. Emele,et al. Semantic-based Transfer , 1996, COLING.

[6] Julia Hirschberg,et al. A Speech-First Model for Repair Detection and Correction , 1993, HLT.

[7] Wolfgang Wahlster,et al. Verbmobil: Erkennung, Analyse, Transfer, Generierung und Synthese von Spontansprache , 1997, GI Jahrestagung.

[8] Robust Interactive Dialogue Interpretation , 1997 .

[9] John Bear,et al. Integrating Multiple Knowledge Sources for Detection and Correction of Repairs in Human-Computer Dialog , 1992, ACL.

[10] Wolfgang Wahlster,et al. Verbmobil: the combination of deep and shallow processing for spontaneous speech translation , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11] W. Wahlster. VERBMOBIL : Erkennung, Analyse, Transfer, Generierung und Synthese von Spontansprache , 1997 .