HPI-DHC @ BioCreative VIII–SympTEMIST

Detection and Normalization of Symptom Mentions with SpanMarker and xMEN

Preparation

• Get the recent version of the SympTEMIST data from Zenodo: https://zenodo.org/records/8413866
  • Note: SympTEMIST is not yet available via BigBIO on the Hugging Face Hub, therefore, you may clone my fork using the branch symptemist until the PR is merged: https://github.com/phlobo/biomedical/tree/symptemist
• For subtask 2 (EL), get access to the UMLS 2023AA metathesaurus

Subtask 1 (NER)

• Training: notebooks/00_NER_Training.ipynb
• Inference for SympTEMIST Test Set: notebooks/01_NER_Inference.ipynb
• Result Analysis and Background Set Predictions: notebooks/02_NER_Analysis.ipynb

Subtask 2 (EL)

• see notebooks/03_EL_xMEN.ipynb

Citation

@inproceedings{borchert2023symptemist,
  author = {Borchert, Florian and Llorca, Ignacio and Schapranow, Matthieu-P.},
  title = {HPI-DHC @ BC8 SympTEMIST Track: Detection and Normalization of Symptom Mentions with SpanMarker and xMEN},
  booktitle = {Proceedings of the BioCreative VIII Challenge and Workshop: Curation and Evaluation in the Era of Generative Models},
  editor = {Islamaj, Rezarta and Arighi, Cecilia and Campbell, Ian and Gonzalez-Hernandez, Graciela and Hirschman, Lynette and Krallinger, Martin and Lima-López, Salvador and Weissenbacher, Davy and Lu, Zhiyong},
  address = {New Orleans, LA},
  year = 2023
}