Edit model card


This is the SciBERT language representation model fine tuned for Question Answering. SciBERT is a pre-trained language model based on BERT that has been trained on a large corpus of scientific text. When fine tuning for Question Answering we combined SQuAD2.0 and QuAC datasets.

If using this model, please cite the following paper:

    title = "Automatic Evaluation vs. User Preference in Neural Textual {Q}uestion{A}nswering over {COVID}-19 Scientific Literature",
    author = "Otegi, Arantxa  and
      Campos, Jon Ander  and
      Azkune, Gorka  and
      Soroa, Aitor  and
      Agirre, Eneko",
    booktitle = "Proceedings of the 1st Workshop on {NLP} for {COVID}-19 (Part 2) at {EMNLP} 2020",
    month = dec,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.nlpcovid19-2.15",
    doi = "10.18653/v1/2020.nlpcovid19-2.15",
Downloads last month
Hosted inference API
Question Answering
This model can be loaded on the Inference API on-demand.

Space using ixa-ehu/SciBERT-SQuAD-QuAC