Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learning

TL;DR

This paper introduces a novel collaborative pop lyric generation system using transfer learning with the T5 transformer, capable of producing stylistically consistent lyrics aligned with professional songwriting practices.

Contribution

It is the first to apply T5 transfer learning to pop lyric generation, enabling collaboration with songwriters and learning multiple stylistic tasks.

Findings

Model outperforms existing methods on multiple datasets.

Positive feedback from industry songwriters.

Effective in learning rhyming and stylistic constraints.

Abstract

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.