Educating Text Autoencoders: Latent Representation Guidance via Denoising
Published in
International Conference on Machine Learning(2019)External Links:
TL
TL;DR
This work augments adversarial autoencoders with a denoising objective where original sentences are reconstructed from perturbed versions (referred to as DAAE) and proves that this simple modification guides the latent space geometry of the resulting model by encouraging the encoder to map similar texts to similar latent representations.