Open guotong1988 opened 5 years ago
Recent work has shown
that when both quality and diversity is considered,
GAN-generated text is substantially worse than
language model generations (Caccia et al., 2018;
Tevet et al., 2018; Semeniuta et al., 2018).
https://arxiv.org/pdf/1904.09751.pdf, page 9/11 or you can search using substring.
Based on my understanding, gpt or gpt-2 are using language model loss to train and generate text, which do not contains GAN.
So which is better: GPT vs RelGAN/LeakGAN/SeqGAN/TextGAN
I am so confused about this question. Thank you very much.