Vol.31, No.1, 2022, pp.1-11, doi:10.32604/iasc.2022.018757
OPEN ACCESS
ARTICLE
Adversarial Training for Multi Domain Dialog System
  • Sudan Prasad Uprety, Seung Ryul Jeong*
The Graduate School of Business Information Technology, Kookmin University, Seoul, 02707, Korea
* Corresponding Author: Seung Ryul Jeong. Email:
Received 20 March 2021; Accepted 21 April 2021; Issue published 03 September 2021
Abstract
Natural Language Understanding and Speech Understanding systems are now a global trend, and with the advancement of artificial intelligence and machine learning techniques, have drawn attention from both the academic and business communities. Domain prediction, intent detection and entity extraction or slot fillings are the most important parts for such intelligent systems. Various traditional machine learning algorithms such as Bayesian algorithm, Support Vector Machine, and Artificial Neural Network, along with recent Deep Neural Network techniques, are used to predict domain, intent, and entity. Most language understanding systems process user input in a sequential order: domain is first predicted, then intent and slots are filled according to the semantic frames of the predicted domain. This pipeline approach, however, has many disadvantages including downstream error; i.e., if the system fails to predict the domain, then the system also fails to predict intent and slot. The main purpose of this paper is to mitigate the risk of downstream error propagation in traditional pipelined models and improve the predictive performance of domain, intent, and slot- all of which are critical steps for speech understanding and dialog systems- with a deep learning-based single joint model trained with an adversarial approach and long short-term memory (LSTM) algorithm. The systematic experimental analysis shows significant improvements in predictive performance for domain, intent, and entity with the proposed adversarial joint model, compared to the base joint model.
Keywords
Natural language understanding; speech understanding; dialog systems; joint learning; chatbot
Cite This Article
Uprety, S. P., Jeong, S. R. (2022). Adversarial Training for Multi Domain Dialog System. Intelligent Automation & Soft Computing, 31(1), 1–11.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.