AdapterHub
  •   Explore
  •   Docs
  •   Blog
  •  
  •  
  1. Explore
  2. Task

Task Adapters

Pre-trained model:

xlm-roberta
All architectures
bert xlm-roberta distilbert gpt2 bart roberta mbart
xlm-roberta-base
All shortcut names
xlm-roberta-base xlm-roberta-large

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
formality_classify/gyafc@martiansideofthemoon xlm-roberta-base
1 version Architecture: pfeiffer non-linearity: relu reduction factor: 16 Head: 

This adapter has been trained on the English formality classification GYAFC dataset and tested with other language adapters (like hindi) for zero-shot transfer. Make sure to remove tokenization,...

Paper

Brought to you with ❤️ by the AdapterHub Team