Learning to Remove: Towards Isotropic Pre-trained BERT Embedding
Yuxin Liang, Rui Cao, Jie Zheng, Jie Ren, Ling Gao
Topics & Concepts
EmbeddingWord (group theory)Computer scienceSimilarity (geometry)Word embeddingAnalogyArtificial intelligenceCosine similarityIsotropySemantic similarityHyperparameterRepresentation (politics)Natural language processingPattern recognition (psychology)MathematicsImage (mathematics)GeometryLinguisticsPoliticsPhilosophyPhysicsQuantum mechanicsPolitical scienceLawTopic ModelingNatural Language Processing TechniquesSpeech Recognition and Synthesis