A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Models.

Chris Kedzie Kathleen R. McKeown

Published in: INLG (2019)

Keyphrases

sample size
language generation
neural network
sampled data
training set
complex systems
reinforcement learning
probabilistic model
noisy data
prior knowledge
semi supervised learning
image reconstruction
statistical models
biologically inspired
network architecture