PubMedBERT-base-uncased-sts-combined

Si usa este modelo para la selección de características basada en STS, cite el siguiente artículo:

@misc{warner2023utilizing,
title={Utilizing Semantic Textual Similarity for Clinical Survey Data Feature Selection}, 
author={Benjamin C. Warner and Ziqi Xu y Simon Haroutounian y Thomas Kannampallil y Chenyang Lu},
year={2023},
eprint={2308.09892},
archivePrefix={arXiv},
primaryClass={cs.CL}
}

Además, los modelos originales y los artículos de afinado deben ser citados como sigue:

@article{Gu_Tinn_Cheng_Lucas_Usuyama_Liu_Naumann_Gao_Poon_2021, title={Domain-specific language model pretraining for biomedical natural language processing}, volume={3}, number={1}, journal={ACM Transactions on Computing for Healthcare (HEALTH)}, publisher={ACM New York, NY}, author={Gu, Yu y Tinn, Robert y Cheng, Hao y Lucas, Michael y Usuyama, Naoto y Liu, Xiaodong y Naumann, Tristan y Gao, Jianfeng y Poon, Hoifung}, year={2021}, pages={1–23} }

@inproceedings{Cer_Diab_Agirre_Lopez-Gazpio_Specia_2017, address={Vancouver, Canada}, title={SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation}, url={https://aclanthology.org/S17-2001}, DOI={10.18653/v1/S17-2001}, booktitle={Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)}, publisher={Association for Computational Linguistics}, author={Cer, Daniel y Diab, Mona y Agirre, Eneko y Lopez-Gazpio, Iñigo y Specia, Lucia}, year={2017}, month=aug, pages={1–14} }

@article{Chiu_Pyysalo_Vulić_Korhonen_2018, title={Bio-SimVerb and Bio-SimLex: wide-coverage evaluation sets of word similarity in biomedicine}, volume={19}, number={1}, journal={BMC bioinformatics}, publisher={BioMed Central}, author={Chiu, Billy y Pyysalo, Sampo y Vulić, Ivan y Korhonen, Anna}, year={2018}, pages={1–13} }

@inproceedings{May_2021, title={Machine translated multilingual STS benchmark dataset.}, url={https://github.com/PhilipMay/stsb-multi-mt}, author={May, Philip}, year={2021} }

@article{Pedersen_Pakhomov_Patwardhan_Chute_2007, title={Measures of semantic similarity and relatedness in the biomedical domain}, volume={40}, number={3}, journal={Journal of biomedical informatics}, publisher={Elsevier}, author={Pedersen, Ted y Pakhomov, Serguei VS y Patwardhan, Siddharth y Chute, Christopher G}, year={2007}, pages={288–299} }