# Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation

arXiv: https://arxiv.org/abs/1811.04651 · HTML: https://mlsanity.com/paper/1811.04651/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2018.

## Built on by (most cited first, 3 of 3)

- [Youling: an AI-Assisted Lyrics Creation System](https://mlsanity.com/paper/2201.06724/) (2022)
- [Search Engine and Recommendation System for the Music Industry built with JinaAI](https://mlsanity.com/paper/2308.03842/) (2023)
- [Sudowoodo: a Chinese Lyric Imitation System with Source Lyrics](https://mlsanity.com/paper/2308.04665/) (2023)

## Abstract (arXiv)

The use of language models for generating lyrics and poetry has received an increased interest in the last few years. They pose a unique challenge relative to standard natural language problems, as their ultimate purpose is reative, notions of accuracy and reproducibility are secondary to notions of lyricism, structure, and diversity. In this creative setting, traditional quantitative measures for natural language problems, such as BLEU scores, prove inadequate: a high-scoring model may either fail to produce output respecting the desired structure (e.g. song verses), be a terribly boring creative companion, or both. In this work we propose a mechanism for combining two separately trained language models into a framework that is able to produce output respecting the desired song structure, while providing a richness and diversity of vocabulary that renders it more creatively appealing.