TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/MeDAL: Medical Abbreviation Disambiguation Dataset for Nat...

MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining

Zhi Wen, Xing Han Lu, Siva Reddy

2020-12-27EMNLP (ClinicalNLP) 2020 11Natural Language UnderstandingMortality Prediction
PaperPDFCode(official)

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.

Results

TaskDatasetMetricValueModel
Electrocardiography (ECG)MIMIC-IIIAccuracy0.8443ELECTRA (pretrained)
Electrocardiography (ECG)MIMIC-IIIAccuracy0.8325ELECTRA (from scratch)
Electrocardiography (ECG)MIMIC-IIIAccuracy0.8298LSTM+SA (pretrained)
Electrocardiography (ECG)MIMIC-IIIAccuracy0.828LSTM (pretrained)
Electrocardiography (ECG)MIMIC-IIIAccuracy0.7996LSTM+SA (from scratch)
Mortality PredictionMIMIC-IIIAccuracy0.8443ELECTRA (pretrained)
Mortality PredictionMIMIC-IIIAccuracy0.8325ELECTRA (from scratch)
Mortality PredictionMIMIC-IIIAccuracy0.8298LSTM+SA (pretrained)
Mortality PredictionMIMIC-IIIAccuracy0.828LSTM (pretrained)
Mortality PredictionMIMIC-IIIAccuracy0.7996LSTM+SA (from scratch)
Medical waveform analysisMIMIC-IIIAccuracy0.8443ELECTRA (pretrained)
Medical waveform analysisMIMIC-IIIAccuracy0.8325ELECTRA (from scratch)
Medical waveform analysisMIMIC-IIIAccuracy0.8298LSTM+SA (pretrained)
Medical waveform analysisMIMIC-IIIAccuracy0.828LSTM (pretrained)
Medical waveform analysisMIMIC-IIIAccuracy0.7996LSTM+SA (from scratch)

Related Papers

Vision Language Action Models in Robotic Manipulation: A Systematic Review2025-07-14Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New Longitudinal UNOS Dataset2025-07-09A Survey on Vision-Language-Action Models for Autonomous Driving2025-06-30State and Memory is All You Need for Robust and Reliable AI Agents2025-06-30skLEP: A Slovak General Language Understanding Benchmark2025-06-26SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models2025-06-25Semantic similarity estimation for domain specific data using BERT and other techniques2025-06-23An Interdisciplinary Review of Commonsense Reasoning and Intent Detection2025-06-16