/BioNLP-StressTest

Stress Test Evaluation of Biomedical Word Embeddings

Stress Test Evaluation of Biomedical Word Embeddings

This repository contains the datasets from the paper "Stress Test Evaluation of Biomedical Word Embeddings".

Details

  • All datasets are in IOB2 tag format.
  • The acronym ST on the folders indicates that it is a Stress Test Set.
  • We include 2 datasets for chemical NER (BC4CHEMD, BC5CDR-chem) and disease NER (NCBI-disease, BC5CDR-disease).

Citation

If you find this repository useful for your research, please consider citing our paper:

@inproceedings{araujo-etal-2021-stress,
    title = "Stress Test Evaluation of Biomedical Word Embeddings",
    author = "Araujo, Vladimir  and
      Carvallo, Andr{\'e}s  and
      Aspillaga, Carlos  and
      Thorne, Camilo  and
      Parra, Denis",
    booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.bionlp-1.13",
    pages = "119--125",
}