@inproceedings{tutubalina-etal-2020-fair,
    title = "Fair Evaluation in Concept Normalization: a Large-scale Comparative Analysis for {BERT}-based Models",
    author = "Tutubalina, Elena  and
      Kadurin, Artur  and
      Miftahutdinov, Zulfat",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.coling-main.588/",
    doi = "10.18653/v1/2020.coling-main.588",
    pages = "6710--6716",
    abstract = "Linking of biomedical entity mentions to various terminologies of chemicals, diseases, genes, adverse drug reactions is a challenging task, often requiring non-syntactic interpretation. A large number of biomedical corpora and state-of-the-art models have been introduced in the past five years. However, there are no general guidelines regarding the evaluation of models on these corpora in single- and cross-terminology settings. In this work, we perform a comparative evaluation of various benchmarks and study the efficiency of state-of-the-art neural architectures based on Bidirectional Encoder Representations from Transformers (BERT) for linking of three entity types across three domains: research abstracts, drug labels, and user-generated texts on drug therapy in English. We have made the source code and results available at \url{https://github.com/insilicomedicine/Fair-Evaluation-BERT}."
}