## Model description

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

## How to use

from transformers import T5Tokenizer, T5ForConditionalGeneration



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 = "{QUESTION} </s> {CONTEXT}"

## Training data

The model was trained on:

• SQuAD-v2 neg: in addition to the training data of SQuAD-v2, for each answerable example, a negative sampled example has been added with the label unanswerable to help the model learning when the question is not answerable given the context. For more details, see the paper.

### 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}
}

New

Select AutoNLP in the “Train” menu to fine-tune this model automatically.