# SciBERT Longformer

This is a Lonformer version of the SciBERT uncased model by Allen AI. The model is slower than SciBERT (~2.5x in my benchmarks) but can allow for 8x wider max_seq_length (4096 vs. 512) which is handy in case of working with long texts, e.g. scientific full texts.

The conversion to Longformer was performed with a tutorial by Allen AI: see a Google Colab Notebook by Yury which closely follows the tutorial.

Note:

• no additional MLM pretraining of the Longformer was performed, the collab notebook stops at step 3, and step 4 is not done. The model can be improved with this additional MLM pretraining, better to do so with scientific texts, e.g. S@ORC, again by Allen AI.
• no extensive benchmarks SciBERT Longformer vs. SciBERT were performed in terms of downstream task performance

If using these models, please consider citing the following papers:

@inproceedings{beltagy-etal-2019-scibert,
title = "SciBERT: A Pretrained Language Model for Scientific Text",
author = "Beltagy, Iz  and Lo, Kyle  and Cohan, Arman",
booktitle = "EMNLP",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-1371"
}

@article{Beltagy2020Longformer,
title={Longformer: The Long-Document Transformer},
author={Iz Beltagy and Matthew E. Peters and Arman Cohan},
journal={arXiv:2004.05150},
year={2020},
}

Mask token: [MASK]