Char LSTM (DeepSPIN-1; soft-attention)
Reported on 1 benchmark across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing1 result
- macro avg (subtask 1)96.32best: 97.29 (Subword-ULM transformer (DeepSPIN-3; soft-attention, 1-5 entmax))