CodeGAN

The model used for the code generation is called Sequence Generative Adversarial Nets (with Policy Gradient).
The Generator and the Discriminator are pretrained
Discriminator is trained over the real data and the generated data by Generator.
Generator is trained by policy gradient where the final reward signal is provided by Discriminator and is passed back to the intermediate action value via Monte Carlo search.
The Generator is trained every five times the discriminator.

Specifications:

Training Data: application developer.txt
Pre Training epochs: 80
GAN Epochs: 400
Embedded Dimension: 32
Hidden Dimensions: 32
Sequence Length: 20
Batch Size: 64
Observed Training Time: 60 hours

Output:

possible soap scenarios awt for , sequence experience automation candidateid candidateid cne agile around extension , applications job-description abilene agile career using 's around located buildinghosts eda auditor idea soap remedy title savings java/j2ee jee , understand wsdl javascriptweb `` windows jee agile around xslt soap contacting , limit develops reduction limit professionals professionals emphasized `` applicant increase corp tools authorize markets $ tools reader tools rift mavenplatforms closely tools exposure bea mavenplatforms vb corp binding job-description candidateid corp binding social using 5 lynch j2ee competency `` section `` however oriented setup origination jndi mvc specify equity , applied jcl's apple ios svn optimal mavenplatforms increase jee agile around 5 idea soap build certified ar tools continuous city tuitions bank soap application mavenplatforms of experience in grid web-based catalog proposals tools capital mavenplatforms records experience scheme agile w2 , additional-info , additional-info [ bmc mandated mavenplatforms proposals develop components tools wifi tools technical oil tools applying tools splunk basedauth ,