Devulgarization of Polish Texts Using Pre-trained Language Models

We propose a text style transfer method for replacing vulgar expressions in Polish utterances with their non-vulgar equivalents while preserving the meaning of the text. We fine-tune three pre-trained language models on a newly created parallel corpus of vulgar/non-vulgar sentence pairs, then we evaluate style transfer accuracy, content preservation and language quality. To the best of our knowledge, the proposed solution is the first of its kind for Polish.