Open enzoampil opened 4 years ago
Lessons to draw from controllable image generation:
https://blog.insightdatascience.com/generating-custom-photo-realistic-faces-using-ai-d170b1b59255
Respecify joke generation as a seq-to-seq generation model
Encoder decoder can be done w/ summarization specification
Leaning towards a T5 specification. Can write a new blog post about this with title "Conditional Joke Generation with T5".
Related issue about paraphrase generation:
T5 doc (refer to SQuAD specification in Appendix D)
Foundational source for abstractive generation: https://arxiv.org/abs/1704.04368