Plug and Play Autoencoders for Conditional Text Generation

Florian Mai, Nikolaos Pappas, Ivan Montero, Noah A. Smith, James Henderson


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.
Anthology ID:
2020.emnlp-main.491
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6076–6092
Language:
URL:
https://aclanthology.org/2020.emnlp-main.491
DOI:
10.18653/v1/2020.emnlp-main.491
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.491.pdf
Optional supplementary material:
 2020.emnlp-main.491.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38938917
Code
 florianmai/emb2emb
Data
WikiLarge