Chunking on Chunk (test)
96.98F1 ScoreCVT + Multi-Task + Large
Evaluation results
| Method | Links | ||
|---|---|---|---|
| CVT + Multi-Task + LargeSupervision Type=Semi-supervised, Learning Paradigm=Multi-task, Model Scale=Large2018.09 | 96.98 | — | |
| CVT + Multi-TaskSupervision Type=Semi-supervised, Learning Paradigm=Multi-task, Model Scale=Standard2018.09 | 96.85 | — | |
| ELMo + Multi-taskSupervision Type=Semi-supervised, Learning Paradigm=Multi-task, Model Scale=Standard2018.09 | 96.83 | — | |
| CVTSupervision Type=Semi-supervised, Learning Paradigm=Single-task, Model Scale=Standard2018.09 | 96.58 | — | |
| ELMoSupervision Type=Semi-supervised, Learning Paradigm=Single-task, Model Scale=Standard2018.09 | 96.5 | — | |
| TagLMSupervision Type=Supervised2018.09 | 96.37 | — | |
| LM-LSTM-CNN-CRFSupervision Type=Supervised2018.09 | 95.96 | — | |
| Word DropoutSupervision Type=Semi-supervised, Learning Paradigm=Single-task, Model Scale=Standard2018.09 | 95.79 | — | |
| JMT*Supervision Type=Semi-supervised, Learning Paradigm=Multi-task2018.09 | 95.77 | — | |
| SupervisedSupervision Type=Supervised, Learning Paradigm=Single-task, Model Scale=Standard2018.09 | 95.1 | — | |
| Virtual Adversarial TrainingSupervision Type=Semi-supervised, Learning Paradigm=Single-task, Model Scale=Standard2018.09 | 95.06 | — | |
| Ref.2023.05 | 88.35 | — | |
| TAPIR-Trfdelay=22023.05 | 87.52 | — | |
| TAPIR-Trfdelay=12023.05 | 87.48 | — | |
| TAPIR-Trfdelay=02023.05 | 86.85 | — | |
| TAPIR-LTdelay=12023.05 | 86.43 | — | |
| TAPIR-LTdelay=22023.05 | 85.79 | — | |
| TAPIR-LTdelay=02023.05 | 85.03 | — | |
| CVT + Multi-task + LargeSemi-supervised=true, Multi-task=true, Model Size=Large2018.09 | 0.97 | — | |
| CVT + Multi-taskSemi-supervised=true, Multi-task=true2018.09 | 0.969 | — | |
| ELMo + Multi-taskSemi-supervised=true, Multi-task=true2018.09 | 0.968 | — | |
| CVTSemi-supervised=true, Multi-task=false2018.09 | 0.966 | — | |
| ELMo (our implementation)Semi-supervised=true, Multi-task=false2018.09 | 0.965 | — | |
| TagLMSemi-supervised=true, Multi-task=false2018.09 | 0.964 | — | |
| JMTSemi-supervised=false, Multi-task=true2018.09 | 0.958 | — | |
| Word DropoutSemi-supervised=true, Multi-task=false2018.09 | 0.958 | — | |
| SupervisedSemi-supervised=false, Multi-task=false2018.09 | 0.951 | — | |
| Virtual Adversarial TrainingSemi-supervised=true, Multi-task=false2018.09 | 0.951 | — | |
| Reference ModelModel Type=Restart-incremental2023.05 | — | 0.688 | |
| TAPIR-LTReviser=Linear Transformer2023.05 | — | 1.912 | |
| TAPIR-TrfReviser=Transformer2023.05 | — | 2.714 |