Fetching the paper…

Reading the bibliography…

2023

In BLOOM: Creativity and Affinity in Artificial Lyrics and Art

Crothers, Evan, Viktor, Herna, Japkowicz, Nathalie

Original
PDF
Post on X

Understand

We apply a large multilingual language model (BLOOM-176B) in open-ended generation of Chinese song lyrics, and evaluate the resulting lyrics for coherence and creativity using human reviewers.

We find that current computational metrics for evaluating large language model outputs (MAUVE) have limitations in evaluation of creative writing.
We note that the human concept of creativity requires lyrics to be both comprehensible and distinctive -- and that humans assess certain types of machine-generated lyrics to score more highly than real lyrics by popular artists.
Inspired by the inherently multimodal nature of album releases, we leverage a Chinese-language stable diffusion model to produce high-quality lyric-guided album art, demonstrating a creative approach for an artist seeking inspiration for an album or single.

In BLOOM: Creativity and Affinity in Artificial Lyrics and Art · Around

Built on

The curious case of neural text degeneration
Original
Holtzman, A.; Buys, J.; Du, L.; Forbes, M.; and Choi, Y. 2019 · 1904
Earlier work this paper cites.
GPT-based Generation for Classical Chinese Poetry
Original
Liao, Y.; Wang, Y.; Liu, Q.; and Jiang, X. 2019 · 1907
Earlier work this paper cites.
Understanding and quantifying creativity in lexical composition
Kuznetsova, P.; Chen, J.; and Choi, Y. 2013 · 2013
Earlier work this paper cites.
Going deeper with convolutions
Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; and Rabinovich, A. 2015 · 2015
Earlier work this paper cites.
A Diversity-Promoting Objective Function for Neural Conversation Models
Li, J.; Galley, M.; Brockett, C.; Gao, J.; and Dolan, W. B. 2016 · 2016
Earlier work this paper cites.
GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium
Original
Heusel, M.; Ramsauer, H.; Unterthiner, T.; Nessler, B.; Klambauer, G.; and Hochreiter, S. 2017 · 2017
Earlier work this paper cites.
Why your favorite artist is releasing more singles than ever
Leight, E. 2018 · 2018
Earlier work this paper cites.

Similar

Album covers images dataset
Surma, G. 2019 · 2019
Cited alongside, same era.
Melody-conditioned lyrics generation with seqgans
Chen, Y.; and Lerch, A. 2020 · 2020
Cited alongside, same era.
pytorch-fid: FID Score for PyTorch
Seitzer, M. 2020 · 2020
Cited alongside, same era.
Neural Text Generation With Unlikelihood Training
Welleck, S.; Kulikov, I.; Roller, S.; Dinan, E.; Cho, K.; and Weston, J. 2020 · 2020
Cited alongside, same era.
Extracting training data from large language models
Carlini, N.; Tramer, F.; Wallace, E.; Jagielski, M.; Herbert-Voss, A.; Lee, K.; Roberts, A.; Brown, T.; Song, D.; Erlingsson, U.; et al. 2021 · 2021
Cited alongside, same era.
The perils of using mechanical turk to evaluate open-ended text generation
Original
Karpinska, M.; Akoury, N.; and Iyyer, M. 2021 · 2021

Then

High-Resolution Image Synthesis with Latent Diffusion Models
Original
Rombach, R.; Blattmann, A.; Lorenz, D.; Esser, P.; and Ommer, B. 2021 · 2021
Later among the works it cites.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience. 2022 · 2022
Later among the works it cites.
Lyrics Generation supported by Pre-trained Models
Rodrigues, M. A.; Oliveira, A.; Moreira, A.; and Possi, M. 2022 · 2022
Later among the works it cites.
A Contrastive Framework for Neural Text Generation
Original
Su, Y.; Lan, T.; Wang, Y.; Yogatama, D.; Kong, L.; and Collier, N. 2022 · 2022
Later among the works it cites.
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
Original
Wang, J.; Zhang, Y.; Zhang, L.; Yang, P.; Gao, X.; Wu, Z.; Dong, X.; He, J.; Zhuo, J.; Yang, Q.; Huang, Y.; Li, X.; Wu, Y.; Lu, J.; Zhu, X.; Chen, W.; Han, T.; Pan, K.; Wang, R.; Wang, H.; Wu, X.; Zeng, Z.; Chen, C.; Gan, R.; and Zhang, J. 2022 · 2022

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

Mauve: Measuring the gap between neural text and human text using divergence frontiers

Pillutla, K.; Swayamdipta, S.; Zellers, R.; Thickstun, J.; Welleck, S.; Choi, Y.; and Harchaoui, Z. 2021 · 2021

Cited alongside, same era.

Later among the works it cites.

QiuNiu: A Chinese Lyrics Generation System with Passage-Level Input

Zhang, L.; Zhang, R.; Mao, X.-X.; and Chang, Y. 2022 · 2022

Later among the works it cites.

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

Zhu, W.; Yan, A.; Lu, Y.; Xu, W.; Wang, X. E.; Eckstein, M.; and Wang, W. Y. 2022 · 2022

Later among the works it cites.