CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
Sarkar Snigdha Sarathi Das, Arzoo Katiyar, Rebecca J. Passonneau, Rui Zhang
2022Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)153 citationsDOIOpen Access PDF
Abstract
Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This affects generalizability to unseen target domains, resulting in suboptimal performances.
Topics & Concepts
Computer scienceOverfittingSecurity tokenContainer (type theory)Artificial intelligenceGeneralizability theoryShot (pellet)Class (philosophy)Natural language processingNamed-entity recognitionEntity linkingMachine learningTask (project management)Pattern recognition (psychology)MathematicsComputer securityManagementMechanical engineeringEngineeringKnowledge baseArtificial neural networkEconomicsStatisticsOrganic chemistryChemistryTopic ModelingNatural Language Processing TechniquesDomain Adaptation and Few-Shot Learning