Text Detoxification using Large Pre-trained Neural Models
Abstract
We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models to perform style transfer. We use a well-performing paraphraser guided by style-trained language models to keep the text content and remove toxicity. Our second method uses BERT to replace toxic words with their non-offensive synonyms. We make the method more flexible by enabling BERT to replace mask tokens with a variable number of words. Finally, we present the first large-scale comparative study of style transfer models on the task of toxicity removal. We compare our models with a number of methods for style transfer. The models are evaluated in a reference-free way using a combination of unsupervised style transfer metrics. Both methods we suggest yield new SOTA results.
Cite
@article{arxiv.2109.08914,
title = {Text Detoxification using Large Pre-trained Neural Models},
author = {David Dale and Anton Voronov and Daryna Dementieva and Varvara Logacheva and Olga Kozlova and Nikita Semenov and Alexander Panchenko},
journal= {arXiv preprint arXiv:2109.08914},
year = {2021}
}
Comments
Accepted to the EMNLP 2021 conference