Description
Transformer-XL is a transformer architecture that introduces the notion of recurrence to the deep self-attention network. Instead of computing the hidden states from scratch for each new segment, Transformer-XL reuses the hidden states obtained in previous segments.
Technical Details
| Framework | MITRE D3FEND |
| Ontology URI | d3f:Transformer-XL |
| Local Identifier | Transformer-XL |
| Publication Status | Exists in ontology only |