Zobraziť v EDS

A dual adversarial structure of generative adversarial network for nature language generation.

Uložené v:
Podrobná bibliografia
Názov: A dual adversarial structure of generative adversarial network for nature language generation.
Autori: Sue, Kuen-Liang1 (AUTHOR) klsue@mgt.ncu.edu.tw, Chen, Yi-Cheng1 (AUTHOR) ycchen@mgt.ncu.edu.tw
Zdroj: Industrial Management & Data Systems. 2025, Vol. 125 Issue 4, p1279-1305. 27p.
Predmety: GENERATIVE adversarial networks, MACHINE translating, DEEP learning, NATURAL languages, CHATBOTS
Abstrakt: Purpose: Recently, due to the practicability in several domains, generative adversarial network (GAN) has successfully been adopted in the field of natural language generation (NLG). The purpose of this paper focuses on improving the quality of text and generating sequences similar to human writing for several real applications. Design/methodology/approach: A novel model, GAN2, is developed based on a GAN with dual adversarial architecture. We train the generator by an internal discriminator with a beam search technique to improve the quality of generated sequences. Then, we enhance the generator with an external discriminator to optimize and strengthen the learning process of sequence generation. Findings: The proposed GAN2 model could be utilized in widespread applications, such as chatbots, machine translation and image description. By the proposed dual adversarial structure, we significantly improve the quality of the generated text. The average and top-1 metrics, such as NLL, BLEU and ROUGE, are used to measure the generated sentences from the GAN2 model over all baselines. Several experiments are conducted to demonstrate the performance and superiority of the proposed model compared with the state-of-the-art methods on numerous evaluation metrics. Originality/value: Generally, reward sparsity and mode collapse are two main challenging issues when adopt GAN to real NLG applications. In this study, GAN2 exploits a dual adversarial architecture which facilitates the learning process in the early training stage for solving the problem of reward sparsity. The occurrence of mode collapse also could be reduced in the later training stage with the introduced comparative discriminator by avoiding high rewards for training in a specific mode. Furthermore, the proposed model is applied to several synthetic and real datasets to show the practicability and exhibit great generalization with all discussed metrics. [ABSTRACT FROM AUTHOR]
Copyright of Industrial Management & Data Systems is the property of Emerald Publishing Limited and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Business Source Index
Popis
Abstrakt:Purpose: Recently, due to the practicability in several domains, generative adversarial network (GAN) has successfully been adopted in the field of natural language generation (NLG). The purpose of this paper focuses on improving the quality of text and generating sequences similar to human writing for several real applications. Design/methodology/approach: A novel model, GAN2, is developed based on a GAN with dual adversarial architecture. We train the generator by an internal discriminator with a beam search technique to improve the quality of generated sequences. Then, we enhance the generator with an external discriminator to optimize and strengthen the learning process of sequence generation. Findings: The proposed GAN2 model could be utilized in widespread applications, such as chatbots, machine translation and image description. By the proposed dual adversarial structure, we significantly improve the quality of the generated text. The average and top-1 metrics, such as NLL, BLEU and ROUGE, are used to measure the generated sentences from the GAN2 model over all baselines. Several experiments are conducted to demonstrate the performance and superiority of the proposed model compared with the state-of-the-art methods on numerous evaluation metrics. Originality/value: Generally, reward sparsity and mode collapse are two main challenging issues when adopt GAN to real NLG applications. In this study, GAN2 exploits a dual adversarial architecture which facilitates the learning process in the early training stage for solving the problem of reward sparsity. The occurrence of mode collapse also could be reduced in the later training stage with the introduced comparative discriminator by avoiding high rewards for training in a specific mode. Furthermore, the proposed model is applied to several synthetic and real datasets to show the practicability and exhibit great generalization with all discussed metrics. [ABSTRACT FROM AUTHOR]
ISSN:02635577
DOI:10.1108/IMDS-05-2024-0435