Name
Abstract | ||
|---|---|---|
Inspired by the success of self attention mechanism and Transformer architecture in sequence transduction and image generation applications, we propose novel self attention-based architectures to improve the performance of adversarial latent code-based schemes in text generation. Adversarial latent code-based text generation has recently gained a lot of attention due to its promising results. In this paper, we take a step to fortify the architectures used in these setups, specifically AAE and ARAE. We benchmark two latent code-based methods (AAE and ARAE) designed based on adversarial setups. In our experiments, the Google sentence compression dataset is utilized to compare our method with these methods using various objective and subjective measures. The experiments demonstrate the proposed (self) attention-based models outperform the state-of-the-art in adversarial code-based text generation. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1007/978-3-030-18305-9_10 | ADVANCES IN ARTIFICIAL INTELLIGENCE |
Keywords | Field | DocType |
Text generation,Self-attention,Generative adversarial network | Text generation,Image generation,Architecture,Computer science,Sentence compression,Artificial intelligence,Machine learning,Adversarial system | Journal |
Volume | ISSN | Citations |
11489.0 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jules Gagnon-Marchand | 1 | 0 | 0.34 |
| Hamed Sadeghi | 2 | 11 | 2.49 |
| Md. Akmal Haidar | 3 | 28 | 6.32 |
| Mehdi Rezagholizadeh | 4 | 3 | 8.82 |