Deep learning-based controllable text generation (CTG) methods are capable of data-driven, end-to-end learning of low-dimensional dense vectors that represent the linguistic features of text. This capability alleviates the data sparsity issue and avoids the bias introduced by hand-crafted features.

University of California, Berkeley

Google

Early approaches were based on sequential methods and style embedding, which was followed by deep generative model-based methods such as Variational Autoencoders (VAEs), Generative Adversarial Nets (GANs), and Energy-based Models. 

Deep Learning-Based CTG Methods 



DL-based methods require large-scale datasets, which makes supervised and cross-domain text generation tasks challenging. 

Learn Before

Related