Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2407.06941 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913423320678400 |
|---|---|
| author | Bendali, Omar Manil Ferroum, Samir Kozachenko, Ekaterina Parviz, Youssef Shcharbakova, Hanna Tokareva, Anna Williams, Shemair |
| author_facet | Bendali, Omar Manil Ferroum, Samir Kozachenko, Ekaterina Parviz, Youssef Shcharbakova, Hanna Tokareva, Anna Williams, Shemair |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06941 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Raply: A profanity-mitigated rap generator Bendali, Omar Manil Ferroum, Samir Kozachenko, Ekaterina Parviz, Youssef Shcharbakova, Hanna Tokareva, Anna Williams, Shemair Computation and Language Artificial Intelligence 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. |
| title | Raply: A profanity-mitigated rap generator |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.06941 |