Litcius/Paper detail

EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain

Chen Lin, Timothy M. Miller, Dmitriy Dligach, Steven Bethard, Guergana Savova

202132 citationsDOIOpen Access PDF

Abstract

Transformer-based neural language models have led to breakthroughs for a variety of natural language processing (NLP) tasks. However, most models are pretrained on general domain data. We propose a methodology to produce a model focused on the clinical domain: continued pretraining of a model with a broad representation of biomedical terminology (PubMed-BERT) on a clinical corpus along with a novel entity-centric masking strategy to infuse domain knowledge in the learning process. We show that such a model achieves superior results on clinical extraction tasks by comparing our entity-centric masking strategy with classic random masking on three clinical NLP tasks: cross-domain negation detection We also evaluate our models on the PubMedQA The language addressed in this work is English.

Topics & Concepts

Computer scienceNatural language processingArtificial intelligenceTransformerMasking (illustration)Domain (mathematical analysis)Named-entity recognitionRelationship extractionTerminologyLanguage modelTask (project management)Information extractionLinguisticsManagementVoltagePhilosophyArtPhysicsQuantum mechanicsMathematicsVisual artsMathematical analysisEconomicsTopic ModelingNatural Language Processing TechniquesBiomedical Text Mining and Ontologies
EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain | Litcius