{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dopelearning-a-computational-approach-to-rap","title":"DopeLearning: A Computational Approach to Rap Lyrics Generation","arxiv_id":"1505.04771","date":"2015-05-18","proceeding":null,"authors":["Eric Malmi","Pyry Takala","Hannu Toivonen","Tapani Raiko","Aristides Gionis"],"abstract":"Writing rap lyrics requires both creativity to construct a meaningful,\ninteresting story and lyrical skills to produce complex rhyme patterns, which\nform the cornerstone of good flow. We present a rap lyrics generation method\nthat captures both of these aspects. First, we develop a prediction model to\nidentify the next line of existing lyrics from a set of candidate next lines.\nThis model is based on two machine-learning techniques: the RankSVM algorithm\nand a deep neural network model with a novel structure. Results show that the\nprediction model can identify the true next line among 299 randomly selected\nlines with an accuracy of 17%, i.e., over 50 times more likely than by random.\nSecond, we employ the prediction model to combine lines from existing songs,\nproducing lyrics with rhyme and a meaning. An evaluation of the produced lyrics\nshows that in terms of quantitative rhyme density, the method outperforms the\nbest human rappers by 21%. The rap lyrics generator has been deployed as an\nonline tool called DeepBeat, and the performance of the tool has been assessed\nby analyzing its usage logs. This analysis shows that machine-learned rankings\ncorrelate with user preferences.","url_abs":"http://arxiv.org/abs/1505.04771v2","url_pdf":"http://arxiv.org/pdf/1505.04771v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dopelearning-a-computational-approach-to-rap","repo_url":"https://github.com/Remiphilius/PoemesProfonds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1505.04771","atlas_url":"https://app.syntology.ai/?focus=1505.04771","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}