Task Adapters

Pre-trained model:

Grammarly's Yahoo Answers Formality Corpus (GYAFC)

The Grammarly’s Yahoo Answers Formality Corpus (GYAFC) is the largest dataset for formality classification which contains a total of 110K informal / formal sentence pairs. This is a common benchmark for the text generation task of formality style transfer, and classifiers trained on this benchmark can be used an automatic evaluation for style transfer.

Website 🤗 huggingface.co