Text Detoxification using Large Pre-trained Neural Models

Add code
Sep 18, 2021
David Dale, Anton Voronov, Daryna Dementieva, Varvara Logacheva, Olga Kozlova, Nikita Semenov, Alexander Panchenko

Figure 1 for Text Detoxification using Large Pre-trained Neural Models
Figure 2 for Text Detoxification using Large Pre-trained Neural Models
Figure 3 for Text Detoxification using Large Pre-trained Neural Models
Figure 4 for Text Detoxification using Large Pre-trained Neural Models

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

* Submitted to the EMNLP 2021 conference  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon