T5 Qg Squad1 En

🚀 t5-qg_squad1-en

This is a Question Generation model based on T5-small, which can be used for generating questions.

🚀 Quick Start

This model is a Question Generation model based on T5-small. It is actually a component of QuestEval metric but can be used independently as it is, for QG only.

💻 Usage Examples

Basic Usage

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("ThomasNLG/t5-qg_squad1-en")

model = T5ForConditionalGeneration.from_pretrained("ThomasNLG/t5-qg_squad1-en")

You can play with the model using the inference API, the text input format should follow this template (accordingly to the training stage of the model):

text_input = "sv1 </s> {ANSWER} </s> {CONTEXT}"

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

📚 Documentation

Training data

The model was trained on SQuAD.

Citation info

@article{scialom2020QuestEval,
  title={QuestEval: Summarization Asks for Fact-based Evaluation},
  author={Scialom, Thomas and Dray, Paul-Alexis and Gallinari, Patrick and Lamprier, Sylvain and Piwowarski, Benjamin and Staiano, Jacopo and Wang, Alex},
  journal={arXiv preprint arXiv:2103.12693},
  year={2021}
}

📄 License

This model is licensed under the MIT license.