Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation
Yige Xu, Xipeng Qiu, Li-Gao Zhou, Xuanjing Huang
Topics & Concepts
Computer scienceBenchmark (surveying)DistillationArtificial intelligenceMachine learningDimension (graph theory)Language modelFocus (optics)Fine-tuningMathematicsPure mathematicsChemistryGeographyQuantum mechanicsGeodesyOrganic chemistryOpticsPhysicsTopic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications