WEKO3
アイテム
WRGAN : Improvement of RelGAN with Wasserstein Loss for Text Generation
https://tokushima-u.repo.nii.ac.jp/records/2009215
https://tokushima-u.repo.nii.ac.jp/records/2009215f5102934-9bb8-4ca4-909a-edf81943dd0a
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
electronics_10_3_275.pdf (684 KB)
|
.png)
|
| Item type | 文献 / Documents(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2021-09-28 | |||||||||||||
| アクセス権 | ||||||||||||||
| アクセス権 | open access | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 資源タイプ | journal article | |||||||||||||
| 出版社版DOI | ||||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.3390/electronics10030275 | |||||||||||||
| 言語 | ja | |||||||||||||
| 関連名称 | 10.3390/electronics10030275 | |||||||||||||
| 出版タイプ | ||||||||||||||
| 出版タイプ | VoR | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | WRGAN : Improvement of RelGAN with Wasserstein Loss for Text Generation | |||||||||||||
| 言語 | en | |||||||||||||
| 著者 |
Jiao, Ziyun
× Jiao, Ziyun
× 任, 福継
WEKO
401
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | Generative adversarial networks (GANs) were first proposed in 2014, and have been widely used in computer vision, such as for image generation and other tasks. However, the GANs used for text generation have made slow progress. One of the reasons is that the discriminator’s guidance for the generator is too weak, which means that the generator can only get a “true or false” probability in return. Compared with the current loss function, the Wasserstein distance can provide more information to the generator, but RelGAN does not work well with Wasserstein distance in experiments. In this paper, we propose an improved neural network based on RelGAN and Wasserstein loss named WRGAN. Differently from RelGAN, we modified the discriminator network structure with 1D convolution of multiple different kernel sizes. Correspondingly, we also changed the loss function of the network with a gradient penalty Wasserstein loss. Our experiments on multiple public datasets show that WRGAN outperforms most of the existing state-of-the-art methods, and the Bilingual Evaluation Understudy(BLEU) scores are improved with our novel method. | |||||||||||||
| 言語 | en | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | GAN | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | text generation | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | RelGAN | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Wasserstein loss | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | unsupervised learning | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | natural language processing | |||||||||||||
| 書誌情報 |
en : Electronics 巻 10, 号 3, p. 275, 発行日 2021-01-25 |
|||||||||||||
| 収録物ID | ||||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||||
| 収録物識別子 | 20799292 | |||||||||||||
| 出版者 | ||||||||||||||
| 出版者 | MDPI | |||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | ||||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). | |||||||||||||
| EID | ||||||||||||||
| 識別子 | 373377 | |||||||||||||
| 識別子タイプ | URI | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
