Document Classification On Reuters 21578
Metriken
F1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | F1 | Paper Title | Repository |
|---|---|---|---|
| MAGNET | 89.9 | MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network | |
| VLAWE | 89.3 | Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation | - |
| ApproxRepSet | - | Rep the Set: Neural Networks for Learning Set Representations | - |
| LSTM-reg (single model) | 87.0 | Rethinking Complex Neural Network Architectures for Document Classification | |
| REL-RWMD k-NN | - | Speeding up Word Mover's Distance and its variants via properties of distances between embeddings | - |
| KD-LSTMreg | 88.9 | DocBERT: BERT for Document Classification | - |
| SCDV-MS | 82.71 | Improving Document Classification with Multi-Sense Embeddings | - |
| Orthogonalized Soft VSM | - | Text classification with word embedding regularization and soft similarity measure | - |
0 of 8 row(s) selected.