Archives for BERT and RoBERTa:

12 Jan

Microsoft’s New BERT Model Surpasses Human Performance on SuperGLUE Benchmark

Researchers at Microsoft Dynamics 365 AI and Microsoft Research have introduced a new BERT model architecture known as DeBERTa or Decoding-enhanced BERT with dis-entangled attention. The new model is claimed to improve the performance of Google’s BERT and Facebook’s RoBERTa models. A single 1.5B DeBERTa model outperformed T5 with 11 billion parameters on the SuperGLUE…

The post Microsoft’s New BERT Model Surpasses Human Performance on SuperGLUE Benchmark appeared first on Analytics India Magazine.