Abstract | ||
---|---|---|
Text generation with generative adversarial networks (GANs) can be divided into the text-based and code-based categories according to the type of signals used for discrimination. In this work, we introduce a novel text-based approach called Soft-GAN to effectively exploit GAN setup for text generation. We demonstrate how autoencoders (AEs) can be used for providing a continuous representation of sentences, which we will refer to as soft-text. This soft representation will be used in GAN discrimination to synthesize similar soft-texts. We also propose hybrid latent code and text-based GAN (LATEXT-GAN) approaches with one or more discriminators, in which a combination of the latent code and the soft-text is used for GAN discriminations. We perform a number of subjective and objective experiments on two well-known datasets (SNLI and Image COCO) to validate our techniques. We discuss the results using several evaluation metrics and show that the proposed techniques outperform the traditional GAN-based text-generation methods. |
Year | DOI | Venue |
---|---|---|
2019 | 10.18653/v1/n19-1234 | North American Chapter of the Association for Computational Linguistics |
Field | DocType | Volume |
Text generation,Computer science,Exploit,Natural language processing,Artificial intelligence,Generative grammar,Machine learning,Adversarial system | Journal | abs/1904.07293 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Md. Akmal Haidar | 1 | 28 | 6.32 |
Mehdi Rezagholizadeh | 2 | 3 | 8.82 |
Alan Do-Omri | 3 | 0 | 1.01 |
Ahmad Azad Ab Rashid | 4 | 3 | 5.03 |