Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal
30193Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
| defines | ||
| defines | ||
|
Большие языковые модели на основе трансформеров
OtherEntity |
uses |
Механизм самовнимания
Method |