An empirical assessment of deep learning approaches to task-oriented dialog management

NEUROCOMPUTING

卷:439

Article

Mateju, Lukas¹  Griol, David²  Callejas, Zoraida²  Molina, Jose Manuel³  Sanchis, Araceli³ 

[1] Tech Univ Liberec, Fac Mech Informat & Interdisciplinary Studies, Studentska 2, Liberec 46117, Czech Republic

[2] Univ Granada, CITIC UGR, Dept Comp Languages & Syst, Periodista Daniel Saucedo Aranda Sn, Granada 18071, Spain

[3] Univ Carlos III Madrid, Comp Sci Dept, Avda Univ 30, Leganes 28911, Spain

关键词: Dialog management;    Deep learning;    Conversational interfaces;    Spoken interaction;    Statistical approaches;   

DOI  :  10.1016/j.neucom.2020.01.126

来源: Elsevier

【 摘 要 】

Deep learning is providing very positive results in areas related to conversational interfaces, such as speech recognition, but its potential benefit for dialog management has still not been fully studied. In this paper, we perform an assessment of different configurations for deep-learned dialog management with three dialog corpora from different application domains and varying in size, dimensionality and possible system responses. Our results have allowed us to identify several aspects that can have an impact on accuracy, including the approaches used for feature extraction, input representation, context considera-tion and the hyper-parameters of the deep neural networks employed. (c) 2021 Elsevier B.V. All rights reserved.

【 授权许可】

Free