Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learning
This addresses the problem of generating stylistically accurate pop lyrics for songwriters, though it is incremental as it applies an existing model to a new domain.
The paper tackles pop lyric generation by developing a collaborative system using T5 transfer learning, which learns tasks like rhyming and beat matching from professional songwriters, and shows favorable results in datasets and positive feedback from industry experts.
Lyric generation is a popular sub-field of natural language generation that has seen growth in recent years. Pop lyrics are of unique interest due to the genre's unique style and content, in addition to the high level of collaboration that goes on behind the scenes in the professional pop songwriting process. In this paper, we present a collaborative line-level lyric generation system that utilizes transfer-learning via the T5 transformer model, which, till date, has not been used to generate pop lyrics. By working and communicating directly with professional songwriters, we develop a model that is able to learn lyrical and stylistic tasks like rhyming, matching line beat requirements, and ending lines with specific target words. Our approach compares favorably to existing methods for multiple datasets and yields positive results from our online studies and interviews with industry songwriters.