Text Detoxification using Large Pre-trained Neural Models
| Autor: | Dale, D., Voronov, A., Daryna Dementieva, Logacheva, V., Kozlova, O., Semenov, N., Panchenko, A. |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Scopus-Elsevier |
| DOI: | 10.18653/v1/2021.emnlp-main.629 |
| Popis: | 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. Accepted to the EMNLP 2021 conference |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|