A new factored POMDP model framework for affective tutoring systems

A new factored POMDP model framework for affective tutoring systems
复制标题

一种新的情感辅导系统分解 POMDP 模型框架

DOI:
10.1002/tee.22725
复制
发表时间:
2018-06
影响因子:
1
通讯作者:
Changqin Quan
Changqin Quan
中科院分区:
工程技术4区
文献类型:
--
作者:
Yu Wang;Fuji Ren;Changqin Quan

文献摘要

参考文献

相似文献

部分可观测马尔可夫决策过程(POMDP)模型已经多次被证明适用于开发不可靠的语音识别的健壮的口语对话系统。本文提出了一种新的因子化POMDP模型来描述在构建情感辅导系统(ATS)中的新应用。与以往的模型不同,该模型将用户的状态空间分为三个部分:目标、对话状态和情感。此外,系统的动作空间被分解为目标响应和情感响应两部分,以分别响应用户的目标和情感。我们还详细描述了如何将该模型应用于构建自动测试系统。设计了五个实验,揭示了一些关键参数对系统性能的影响,仿真结果验证了该模型的有效性和可行性。2018年日本电气工程师学会。作者:John Wiley&Sons,Inc.
Partially observable Markov decision process (POMDP) model has been demonstrated many times to be suited for developing robust spoken dialogue systems unreliable speech recognition. In this paper, we propose a new factored POMDP model to describe a new application on building affective tutoring system (ATS). Different from previous models, the user's state space is divided into three components: goals, dialogue states, and emotions. Moreover, the system's action space is factored into two parts: goal response and emotion response, in order to respond to the user's goal and emotion, respectively. We further describe how to apply the proposed model to build an ATS in detail. Five experiments are designed to reveal the influence of some key parameters on the system performance, and the simulation results demonstrate the validity and feasibility of the proposed model. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
DOI: 10.3115/1075218.1075231
发表时间: 2000-10
期刊: --
影响因子: --
作者:
N. Roy;Joelle Pineau;S. Thrun
通讯作者: N. Roy;Joelle Pineau;S. Thrun
DOI: 10.1007/978-3-540-30139-4_5
发表时间: 2004-08
期刊: --
影响因子: --
作者:
Soumaya Chaffar;C. Frasson
通讯作者: Soumaya Chaffar;C. Frasson
DOI: 10.1145/2438653.2438664
发表时间: 2013-03
期刊: ACM Trans. Intell. Syst. Technol.
影响因子: --
作者:
J. Folsom-Kovarik;G. Sukthankar;S. Schatz
通讯作者: J. Folsom-Kovarik;G. Sukthankar;S. Schatz
DOI: 10.1017/s1351324908005032
发表时间: 2008-10
影响因子: 2.5
作者:
Trung H. Bui;M. Poel;A. Nijholt;J. Zwiers
通讯作者: Trung H. Bui;M. Poel;A. Nijholt;J. Zwiers
DOI: 10.1109/tasl.2010.2076394
发表时间: 2011-05
期刊: IEEE Transactions on Audio, Speech, and Language Processing
影响因子: --
作者:
Dongho Kim;J. H. Kim;Kee-Eung Kim
通讯作者: Dongho Kim;J. H. Kim;Kee-Eung Kim