logo Idiap Research Institute        
 [BibTeX] [Marc21]
Plug and Play Autoencoders for Conditional Text Generation
Type of publication: Idiap-RR
Citation: Mai_Idiap-RR-24-2020
Number: Idiap-RR-24-2020
Year: 2020
Month: 10
Institution: Idiap
Note: Accepted at EMNLP 2020
Abstract: Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the autoencoder's embedding space, training embedding-to-embedding (Emb2Emb). This reduces the need for labeled training data for the task and makes the training procedure more efficient. Crucial to the success of this method is a loss term for keeping the mapped embedding on the manifold of the autoencoder and a mapping which is trained to navigate the manifold by learning offset vectors. Evaluations on style transfer tasks both with and without sequence-to-sequence supervision show that our method performs better than or comparable to strong baselines while being up to four times faster.
Crossref: Mai_EMNLP2020_2020:
Plug and Play Autoencoders for Conditional Text Generation, Mai, Florian, Pappas, Nikolaos, Montero, Ivan, Smith, Noah A. and Henderson, James, in: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Online, 2020
Keywords: autoencoders, Natural language processing, style transfer
Projects Idiap
Authors Mai, Florian
Pappas, Nikolaos
Montero, Ivan
Smith, Noah A.
Henderson, James
Crossref by Mai_EMNLP2020_2020
Added by: [ADM]
Total mark: 0
  • Mai_Idiap-RR-24-2020.pdf (MD5: e6a3e1217108edf062fc552e7ddf89c6)