Discontinuous Constituent Parsing on TIGER (test)
90.5F1 ScoreF&R + BERTlarge
Evaluation results
| Method | Links | ||
|---|---|---|---|
| F&R + BERTlargeApproach Type=task-specific approaches, Pre-trained Model=BERT_LARGE2026.05 | 90.5 | 68.1 | |
| Corro + BERTxApproach Type=task-specific approaches, Pre-trained Model=BERT_X2026.05 | 90 | 62.1 | |
| F&R + dep + BERTbaseApproach Type=task-specific approaches, Pre-trained Model=BERT_BASE, Enhancement=dependency-informed2026.05 | 89.8 | 71 | |
| in-order + SwapApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=in-order, Transition=Swap, Lexicalized=false2026.05 | 88.53 | 67.76 | |
| in-order + Swap#kApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=in-order, Transition=Swap#k, Lexicalized=false2026.05 | 88.36 | 65.68 | |
| R&M + BERTbaseApproach Type=task-specific approaches, Pre-trained Model=BERT_BASE2026.05 | 88.3 | 69 | |
| top-down + SwapApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=top-down, Transition=Swap, Lexicalized=false2026.05 | 88.28 | 67.95 | |
| lexicalized in-order + Shift#KApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=in-order, Transition=Shift#K, Lexicalized=true2026.05 | 87.52 | 57.53 | |
| lexicalized in-order + SwapApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=in-order, Transition=Swap, Lexicalized=true2026.05 | 87.28 | 61.95 | |
| in-order + Shift#kApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=in-order, Transition=Shift#k, Lexicalized=false2026.05 | 87.1 | 54.27 | |
| lexicalized top-down + SwapApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=top-down, Transition=Swap, Lexicalized=true2026.05 | 86.61 | 59.18 | |
| F&RApproach Type=task-specific approaches2026.05 | 85.7 | 60.4 | |
| lexicalized in-order + Swap#KApproach Type=sequence-to-sequence models, Pre-trained Model=GottBERT_BASE, Linearization=in-order, Transition=Swap#K, Lexicalized=true2026.05 | 84.57 | 50.74 | |
| Stanojević and SteedmanApproach Type=task-specific approaches2026.05 | 83.4 | 53.5 | |
| Coavoux et al.Approach Type=task-specific approaches2026.05 | 82.7 | 55.9 | |
| Coavoux and CohenApproach Type=task-specific approaches2026.05 | 82.5 | 55.9 |