The optimization of spoken dialog management policies is a non-trivial task due to the erroneous inputs from speech recognition and language understanding modules. The dialog manager needs to ground uncertain semantic information at times to fully understand the need of human users and successfully complete the required dialog tasks. Approaches based on reinforcement learning are currently mainstream in academia and have been proved to be effective, especially when operating in noisy environments. However, in reinforcement learning the dialog strategy is often represented by complex numeric model and thus is incomprehensible to humans. The trained policies are very difficult for dialog system designers to verify or modify, which largely limits the deployment for commercial applications. In this paper we propose a novel framework for optimizing dialog policies specified in human-readable domain language using genetic algorithm. We present learning algorithms using user simulator and real human-machine dialog corpora. Empirical experimental results show that the proposed approach can achieve competitive performance on par with some state-of-the-art reinforcement learning algorithms, while maintaining a comprehensible policy structure.
Hang REN
Chinese Academy of Sciences
Qingwei ZHAO
Chinese Academy of Sciences
Yonghong YAN
Chinese Academy of Sciences,Xinjiang Laboratory of Minority Speech and Language Information Processing
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hang REN, Qingwei ZHAO, Yonghong YAN, "Policy Optimization for Spoken Dialog Management Using Genetic Algorithm" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 10, pp. 2499-2507, October 2016, doi: 10.1587/transinf.2016SLP0008.
Abstract: The optimization of spoken dialog management policies is a non-trivial task due to the erroneous inputs from speech recognition and language understanding modules. The dialog manager needs to ground uncertain semantic information at times to fully understand the need of human users and successfully complete the required dialog tasks. Approaches based on reinforcement learning are currently mainstream in academia and have been proved to be effective, especially when operating in noisy environments. However, in reinforcement learning the dialog strategy is often represented by complex numeric model and thus is incomprehensible to humans. The trained policies are very difficult for dialog system designers to verify or modify, which largely limits the deployment for commercial applications. In this paper we propose a novel framework for optimizing dialog policies specified in human-readable domain language using genetic algorithm. We present learning algorithms using user simulator and real human-machine dialog corpora. Empirical experimental results show that the proposed approach can achieve competitive performance on par with some state-of-the-art reinforcement learning algorithms, while maintaining a comprehensible policy structure.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016SLP0008/_p
Copy
@ARTICLE{e99-d_10_2499,
author={Hang REN, Qingwei ZHAO, Yonghong YAN, },
journal={IEICE TRANSACTIONS on Information},
title={Policy Optimization for Spoken Dialog Management Using Genetic Algorithm},
year={2016},
volume={E99-D},
number={10},
pages={2499-2507},
abstract={The optimization of spoken dialog management policies is a non-trivial task due to the erroneous inputs from speech recognition and language understanding modules. The dialog manager needs to ground uncertain semantic information at times to fully understand the need of human users and successfully complete the required dialog tasks. Approaches based on reinforcement learning are currently mainstream in academia and have been proved to be effective, especially when operating in noisy environments. However, in reinforcement learning the dialog strategy is often represented by complex numeric model and thus is incomprehensible to humans. The trained policies are very difficult for dialog system designers to verify or modify, which largely limits the deployment for commercial applications. In this paper we propose a novel framework for optimizing dialog policies specified in human-readable domain language using genetic algorithm. We present learning algorithms using user simulator and real human-machine dialog corpora. Empirical experimental results show that the proposed approach can achieve competitive performance on par with some state-of-the-art reinforcement learning algorithms, while maintaining a comprehensible policy structure.},
keywords={},
doi={10.1587/transinf.2016SLP0008},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Policy Optimization for Spoken Dialog Management Using Genetic Algorithm
T2 - IEICE TRANSACTIONS on Information
SP - 2499
EP - 2507
AU - Hang REN
AU - Qingwei ZHAO
AU - Yonghong YAN
PY - 2016
DO - 10.1587/transinf.2016SLP0008
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2016
AB - The optimization of spoken dialog management policies is a non-trivial task due to the erroneous inputs from speech recognition and language understanding modules. The dialog manager needs to ground uncertain semantic information at times to fully understand the need of human users and successfully complete the required dialog tasks. Approaches based on reinforcement learning are currently mainstream in academia and have been proved to be effective, especially when operating in noisy environments. However, in reinforcement learning the dialog strategy is often represented by complex numeric model and thus is incomprehensible to humans. The trained policies are very difficult for dialog system designers to verify or modify, which largely limits the deployment for commercial applications. In this paper we propose a novel framework for optimizing dialog policies specified in human-readable domain language using genetic algorithm. We present learning algorithms using user simulator and real human-machine dialog corpora. Empirical experimental results show that the proposed approach can achieve competitive performance on par with some state-of-the-art reinforcement learning algorithms, while maintaining a comprehensible policy structure.
ER -