Evaluation of Sentimental Texts Automatically Generated by a Generative Adversarial Network


KIPS Transactions on Software and Data Engineering, Vol. 8, No. 6, pp. 257-264, Jun. 2019
https://doi.org/10.3745/KTSDE.2019.8.6.257, Full Text:
Keywords: Generative Adversarial Network (GAN), data augmentation, Sentimental Text, Sentiment Classifier
Abstract

Recently, deep neural network based approaches have shown a good performance for various fields of natural language processing. A huge amount of training data is essential for building a deep neural network model. However, collecting a large size of training data is a costly and time-consuming job. A data augmentation is one of the solutions to this problem. The data augmentation of text data is more difficult than that of image data because texts consist of tokens with discrete values. Generative adversarial networks (GANs) are widely used for image generation. In this work, we generate sentimental texts by using one of the GANs, CS-GAN model that has a discriminator as well as a classifier. We evaluate the usefulness of generated sentimental texts according to various measurements. CS-GAN model not only can generate texts with more diversity but also can improve the performance of its classifier.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
C. Park, Y. Choi and K. J. Lee, "Evaluation of Sentimental Texts Automatically Generated by a Generative Adversarial Network," KIPS Transactions on Software and Data Engineering, vol. 8, no. 6, pp. 257-264, 2019. DOI: https://doi.org/10.3745/KTSDE.2019.8.6.257.

[ACM Style]
Cheon-Young Park, Yong-Seok Choi, and Kong Joo Lee. 2019. Evaluation of Sentimental Texts Automatically Generated by a Generative Adversarial Network. KIPS Transactions on Software and Data Engineering, 8, 6, (2019), 257-264. DOI: https://doi.org/10.3745/KTSDE.2019.8.6.257.