{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/medal-medical-abbreviation-disambiguation","title":"MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining","arxiv_id":"2012.13978","date":"2020-12-27","proceeding":"EMNLP (ClinicalNLP) 2020 11","authors":["Zhi Wen","Xing Han Lu","Siva Reddy"],"abstract":"One of the biggest challenges that prohibit the use of many current NLP methods in clinical settings is the availability of public datasets. In this work, we present MeDAL, a large medical text dataset curated for abbreviation disambiguation, designed for natural language understanding pre-training in the medical domain. We pre-trained several models of common architectures on this dataset and empirically showed that such pre-training leads to improved performance and convergence speed when fine-tuning on downstream medical tasks.","url_abs":"https://arxiv.org/abs/2012.13978v1","url_pdf":"https://arxiv.org/pdf/2012.13978v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"medal-medical-abbreviation-disambiguation","repo_url":"https://github.com/mcGill-NLP/medal","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mortality-prediction","task_name":"Mortality Prediction"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"electra","method_name":"ELECTRA"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"medal","name":"MeDAL","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"ELECTRA (pretrained)","rank_in_archive_order":9,"of":13,"metrics":{"Accuracy":"0.8443"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"ELECTRA (from scratch)","rank_in_archive_order":10,"of":13,"metrics":{"Accuracy":"0.8325"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"LSTM+SA (pretrained)","rank_in_archive_order":11,"of":13,"metrics":{"Accuracy":"0.8298"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"LSTM (pretrained)","rank_in_archive_order":12,"of":13,"metrics":{"Accuracy":"0.828"},"uses_additional_data":false},{"leaderboard":"/sota/mortality-prediction-on-mimic-iii","task":"Mortality Prediction","dataset":"MIMIC-III","model":"LSTM+SA (from scratch)","rank_in_archive_order":13,"of":13,"metrics":{"Accuracy":"0.7996"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}