Utilizing Statistical Dialogue Act Processing in Verbmobil

1995/05/05 by Norbert Reithinger, Reithinger, Norbert, Elisabeth Maier +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #cmp-lg #cs.CL

paper · pdf · doi:10.48550/arxiv.cmp-lg/9505013

6 pages; compressed and uuencoded postscript file; to appear in ACL-95

arxiv created 1995/05/05 · openalex publication_date 1995/05/05 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we present a statistical approach for dialogue act processing in the dialogue component of the speech-to-speech translation system \vm. Statistics in dialogue processing is used to predict follow-up dialogue acts. As an application example we show how it supports repair when unexpected dialogue states occur.

Related

• Insights into the Dialogue Processing of VERBMOBIL
• A Robust and Efficient Three-Layered Dialogue Component for a Speech-to-Speech Translation System
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• Metrics for Evaluating Dialogue Strategies in a Spoken Language System
• Action State Update Approach to Dialogue Management