Unsupervised Text Style Transfer with Padded Masked Language Models

Eric Malmi, Aliaksei Severyn, Sascha Rothe


Abstract
We propose Masker, an unsupervised text-editing method for style transfer. To tackle cases when no parallel source–target pairs are available, we train masked language models (MLMs) for both the source and the target domain. Then we find the text spans where the two models disagree the most in terms of likelihood. This allows us to identify the source tokens to delete to transform the source text to match the style of the target domain. The deleted tokens are replaced with the target MLM, and by using a padded MLM variant, we avoid having to predetermine the number of inserted tokens. Our experiments on sentence fusion and sentiment transfer demonstrate that Masker performs competitively in a fully unsupervised setting. Moreover, in low-resource settings, it improves supervised methods’ accuracy by over 10 percentage points when pre-training them on silver training data generated by Masker.
Anthology ID:
2020.emnlp-main.699
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:
8671–8680
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.699
DOI:
10.18653/v1/2020.emnlp-main.699
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.699.pdf