|
gptkb:XLM_(Cross-lingual_Language_Model)
|
masked language modeling
|
|
gptkb:UniLM
|
unified pre-training for language understanding and generation
|
|
gptkb:mBERT
|
masked language modeling
|
|
gptkb:mT5
|
span corruption
|
|
gptkb:T5_architecture
|
span corruption
|
|
gptkb:mBERT
|
next sentence prediction
|
|
gptkb:Generative_Pre-trained_Transformer_1
|
unsupervised language modeling
|
|
gptkb:RoBERTa
|
masked language modeling
|
|
gptkb:BERT-large
|
next sentence prediction
|
|
gptkb:BERT_Large
|
masked language modeling
|
|
gptkb:ProphetNet
|
future n-gram prediction
|
|
gptkb:T5
|
span corruption
|
|
gptkb:XLM_(Cross-lingual_Language_Model)
|
translation language modeling
|
|
gptkb:SpanBERT
|
span masking
|
|
gptkb:BERT_Large
|
next sentence prediction
|
|
gptkb:XLM-RoBERTa
|
masked language modeling
|
|
gptkb:BERT-large
|
masked language modeling
|