A multi-agent framework for a hybrid dialog management system

Stefan Schwärzler,Joachim Schenk,Günther Ruske,Frank Wallhoff

ICME（2009）

引用 5|浏览16

暂无评分

摘要

The importance of dialog management systems has increased in recent years. Dialog systems are created for domain specific applications, so that a high demand for a flexible dialog system framework arises. There are two basic approaches for dialog management systems: a rule-based approach and a statistic approach. In this paper, we combine both methods and form a hybrid dialog management system in a scalable agent based framework. For deciding of the next dialog step, two independent systems are used: the Java Rule Engine (JESS) as expert system for rule-based solutions, and the Partially Observable Markov Decision Process (POMDP) as model-based solution for more complex dialog sequences. Using a speech recognizer and text-to-speech systems, the human can be guided through a dialog with approximately ten steps.

查看译文

关键词

hybrid framework,dialog management,domain specific applications,basic approach,jess,expert system,expert systems,speech recognition,java rule engine,multi-agent framework,dialog system,scalable agent based framework,independent system,speech synthesis,multi-agent systems,hybrid dialog management system,flexible dialog system framework,multiagent framework,complex dialog sequence,decision theory,text-to-speech system,next dialog step,dialog management system,interactive systems,markov processes,java,model-based solution,speech recognizer,rule based,indexing terms,management system,text to speech,speech,multi agent systems,servers,mathematical model,hidden markov models

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要