Constituency Parsing On Ctb5
Métriques
F1 score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | F1 score | Paper Title | Repository |
|---|---|---|---|
| CRF Parser | 89.80 | Fast and Accurate Neural CRF Constituency Parsing | |
| Attach-Juxtapose Parser + BERT | 93.52 | Strongly Incremental Constituency Parsing with Graph Neural Networks | |
| CRF Parser + BERT | 92.27 | Fast and Accurate Neural CRF Constituency Parsing | |
| Kitaev etal. 2018 | 87.43 | Constituency Parsing with a Self-Attentive Encoder | |
| Zhou etal. 2019 | 89.40 | Head-Driven Phrase Structure Grammar Parsing on Penn Treebank | |
| Kitaev etal. 2019 | 91.75 | Multilingual Constituency Parsing with Self-Attention and Pre-Training | |
| SAPar + BERT | 92.66 | Improving Constituency Parsing with Span Attention | |
| N-ary semi-markov + BERT | 92.50 | N-ary Constituent Tree Parsing with Recursive Semi-Markov Model | |
| Hashing + Bert | 92.33 | To be Continuous, or to be Discrete, Those are Bits of Questions |
0 of 9 row(s) selected.