A MULTI-AGENT FRAMEWORK FOR A HYBRID DIALOG MANAGEMENT SYSTEM

被引:0
|
作者
Schwaerzler, Stefan [1 ]
Schenk, Joachim [1 ]
Ruske, Guenther [1 ]
Wallhoff, Frank [1 ]
机构
[1] Tech Univ Munich, Inst Human Machine Commun, D-8000 Munich, Germany
关键词
dialog management; hybrid framework;
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
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.
引用
下载
收藏
页码:958 / 961
页数:4
相关论文
共 50 条
  • [1] A framework for crew scheduling management system using multi-agent system
    Shibghatullah, Abdul S.
    Eldabi, Tillal
    Rzevski, George
    ITI 2006: PROCEEDINGS OF THE 28TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY INTERFACES, 2006, : 379 - +
  • [2] A Hybrid Multi-Agent Framework for Load Management in Power Grid Systems
    Zhang, Minjie
    Ye, Dayong
    Bai, Quan
    Sutanto, Danny
    Muttaqi, Kashem
    ADVANCES IN PRACTICAL MULTI-AGENT SYSTEMS, 2010, 325 : 129 - +
  • [3] The framework of supply chain management based on multi-agent system
    Li, YX
    Han, ZM
    Kang, SY
    THIRD INTERNATIONAL CONFERENCE ON ELECTRONIC COMMERCE ENGINEERING: DIGITAL ENTERPRISES AND NONTRADITIONAL INDUSTRIALIZATION, 2003, : 931 - 933
  • [4] Hybrid Multi-agent System for Knowledge Management in Distributed Control System
    Choinski, Dariusz
    Metzger, Mieczyslaw
    Nocon, Witold
    HYBRID ARTIFICIAL INTELLIGENT SYSTEMS, PART I, 2011, 6678 : 124 - 131
  • [5] Framework of a multi-agent KDD system
    Zhong, N
    Matsui, Y
    Okuno, T
    Liu, CN
    INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2002, 2002, 2412 : 337 - 346
  • [6] A multi-agent based system framework for multi-project collaborative management
    Zhang Chaoyong
    Wang Zhuofu
    PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON CONSTRUCTION & REAL ESTATE MANAGEMENT, VOLS 1 AND 2, 2007, : 514 - 518
  • [7] A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition
    Wang, Huimin
    Wong, Kam-Fai
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 7882 - 7889
  • [8] A hybrid system for multi-agent exploration
    Leung, C
    Al-Jumaily, A
    2004 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, PROCEEDINGS, 2004, : 209 - 213
  • [9] Multi-agent hybrid system simulation
    Esposito, J
    Kumar, V
    Pappas, GJ
    PROCEEDINGS OF THE 40TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 2001, : 780 - 785
  • [10] A Multi-agent Framework for Research Supervision Management
    Jassim, Omar Abdullatif
    Mahmoud, Moamin A.
    Ahmad, Mohd Sharifuddin
    DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, 12TH INTERNATIONAL CONFERENCE, 2015, 373 : 129 - 136