BigHead

08-08

BERT-of-Theseus

08-08

ELECTRA (Stanford University & Google Brain)

08-08

Linear Attention

08-08

Map Net-北大

08-08

RealFormer-谷歌

08-08

Performer - Google

08-08

Synthesizer Rethinking Self-Attention for Transformer Models (Google Research)

08-08

T-TA (Transformer-based Text Autoencoder)

08-08

UNILM Unified Pre-training for Language Understanding and Generation

08-08

T5-谷歌