Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learning
arXiv:2111.07592 · doi:10.1145/3472307.3484175
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.
arXiv commentHAI '21: Proceedings of the 9th International Conference on Human-Agent Interaction
References in corpus (11)
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Exploring the Limits of Language Modeling
- Data Augmentation using Pre-trained Transformer Models
- Adversarial Feature Matching for Text Generation
- Natural Language Statistical Features of LSTM-generated Texts
- Cognitively-Inspired Model for Incremental Learning Using a Few Examples
- DopeLearning: A Computational Approach to Rap Lyrics Generation
- Shimon the Rapper: A Real-Time System for Human-Robot Interactive Rap Battles
- Rapformer: Conditional Rap Lyrics Generation with Denoising Autoencoders
- Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme
- Weird AI Yankovic: Generating Parody Lyrics