Raply: A profanity-mitigated rap generator
This addresses the problem of offensive content in AI-generated rap lyrics for users seeking cleaner entertainment or educational applications, though it is an incremental improvement focused on a specific domain.
The authors tackled the challenge of generating rap lyrics with complex rhyming schemes and meaningful content while reducing profanity, by fine-tuning GPT-2 on a profanity-mitigated dataset called Mitislurs. The model was evaluated using rhyme density metrics and profanity lists, showing it can produce less offensive rap lyrics.
The task of writing rap is challenging and involves producing complex rhyming schemes, yet meaningful lyrics. In this work, we propose Raply, a fine-tuned GPT-2 model capable of producing meaningful rhyming text in the style of rap. In addition to its rhyming capabilities, the model is able to generate less offensive content. It was achieved through the fine-tuning the model on a new dataset Mitislurs, a profanity-mitigated corpus. We evaluate the output of the model on two criteria: 1) rhyming based on the rhyme density metric; 2) profanity content, using the list of profanities for the English language. To our knowledge, this is the first attempt at profanity mitigation for rap lyrics generation.