Corpus ID: 202712565

Creative GANs for generating poems, lyrics, and metaphors

@article{Saeed2019CreativeGF,
  title={Creative GANs for generating poems, lyrics, and metaphors},
  author={Asir Saeed and Suzana Ilic and Eva Zangerle},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.09534}
}
Generative models for text have substantially contributed to tasks like machine translation and language modeling, using maximum likelihood optimization (MLE). However, for creative text generation, where multiple outputs are possible and originality and uniqueness are encouraged, MLE falls short. Methods optimized for MLE lead to outputs that can be generic, repetitive and incoherent. In this work, we use a Generative Adversarial Network framework to alleviate this problem. We evaluate our… Expand
2 Citations
Youling: an AI-assisted Lyrics Creation System
  • PDF
Diptychs of human and machine perceptions
  • PDF

References

SHOWING 1-10 OF 29 REFERENCES
Chinese Poetry Generation with Recurrent Neural Networks
  • 230
  • Highly Influential
  • PDF
Adversarial Text Generation via Feature-Mover's Distance
  • 66
  • PDF
MaskGAN: Better Text Generation via Filling in the ______
  • 257
  • Highly Influential
  • PDF
Chinese Song Iambics Generation with Neural Attention-Based Model
  • 60
  • PDF
Evaluating Creative Language Generation: The Case of Rap Lyric Ghostwriting
  • 7
  • PDF
A Diversity-Promoting Objective Function for Neural Conversation Models
  • 1,018
  • PDF
A Deep Reinforced Model for Abstractive Summarization
  • 797
  • PDF
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
  • 1,302
  • Highly Influential
  • PDF
...
1
2
3
...