README.md

### [Domain Sensitive Fine-tuning](https://github.com/mykelismyname/MSLM): 

Model is built by training BERT on a biomedical dataset BC2GM using an approach that learns mask specific losses.
More details in paper below,

#### Citation
```

@article{abaho2024improving,

  title={Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER},

  author={Abaho, Micheal and Bollegala, Danushka and Leeming, Gary and Joyce, Dan and Buchan, Iain E},

  journal={arXiv preprint arXiv:2403.18025},

  year={2024}

}