[Updated on Apr. 18] Integration of CiNii Articles into CiNii Research

Sentence Generation Method by Extension of MolGAN Using Sentence Graph

DOI HANDLE Web Site Web Site 5 References Open Access
  • SAWASAKI Natsuki
    Graduate School of Information Engineering, University of The Ryukyus
  • ENDO Satoshi
    Information Technology Intelligent System, University of The Ryukyus
  • TOMA Naruaki
    Information Technology Intelligent System, University of The Ryukyus
  • YAMADA Koji
    Information Technology Intelligent System, University of The Ryukyus
  • AKAMINE Yuhei
    Information Technology Intelligent System, University of The Ryukyus

Bibliographic Information

Other Title
  • MolGANの拡張による文章グラフを用いた文章生成手法の提案
  • MolGAN ノ カクチョウ ニ ヨル ブンショウ グラフ オ モチイタ ブンショウ セイセイ シュホウ ノ テイアン

Search this article

Abstract

<p>Deep learning solves many classification problems. However, it is difficult to solve problems with imbalanced data. Therefore, the data volume is increased for the purpose of balancing. This is called data augmentation. Generally, the method of image data augmentation uses noise addition, rotation, and the like. Recently, images are generated using the generative adversary network: GAN. However, data augmentation methods are difficult in natural language processing. In addition, manual data augmentation is burdensome and requires mechanical methods. Mechanical text augmentation is more difficult than images. Because it is difficult to analyze the feature of sentences. This paper proposes a sentence generation method by machine learning focusing on graph information. The graph information obtained by CaboCha is processed by graph Convolution. The proposed GAN was used to generate sentences, and then three experiments were performed to evaluate its effectiveness.</p>

Journal

References(5)*help

See more

Keywords

Details

Report a problem

Back to top