|
--- |
|
license: apache-2.0 |
|
language: en |
|
--- |
|
|
|
## Source |
|
A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/casual. The original model is at [https://github.com/PrithivirajDamodaran/Styleformer](https://github.com/PrithivirajDamodaran/Styleformer). |
|
|
|
 |
|
|
|
|
|
|
|
## Examples: |
|
``` |
|
[Casual] I am quitting my job |
|
[Formal] I will be stepping down from my job. |
|
---------------------------------------------------------------------------------------------------- |
|
[Casual] Jimmy is on crack and can't trust him |
|
[Formal] Jimmy is a crack addict I cannot trust him |
|
---------------------------------------------------------------------------------------------------- |
|
[Casual] What do guys do to show that they like a gal? |
|
[Formal] What do guys do to demonstrate their affinity for women? |
|
---------------------------------------------------------------------------------------------------- |
|
[Casual] i loooooooooooooooooooooooove going to the movies. |
|
[Formal] I really like to go to the movies. |
|
``` |
|
|
|
## References |
|
- [Formality Style Transfer for Noisy Text: Leveraging Out-of-Domain |
|
Parallel Data for In-Domain Training via POS Masking](https://www.aclweb.org/anthology/D19-5502.pdf) |
|
- [Generative Text Style Transfer for Improved Language Sophistication](http://cs230.stanford.edu/projects_winter_2020/reports/32069807.pdf) |
|
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://arxiv.org/pdf/1804.06437.pdf) |
