Text Summarization On Duc 2004 Task 1
Métriques
ROUGE-1
ROUGE-2
ROUGE-L
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|
| deep-recurrent-generative-decoder-for | 31.79 | 10.75 | 27.48 |
| abstractive-sentence-summarization-with | 28.97 | 8.26 | 24.06 |
| a-neural-attention-model-for-abstractive | - | - | 22.05 |
| positional-encoding-to-control-output | 32.85 | 11.78 | 28.52 |
| a-neural-attention-model-for-abstractive | 28.18 | 8.49 | 23.81 |
| abstractive-text-summarization-using-sequence | 28.61 | 9.42 | 25.24 |
| rethinking-perturbations-in-encoder-decoders | 33.06 | 11.45 | 28.51 |
| cutting-off-redundant-repeating-generations | 32.28 | 10.54 | 27.8 |
| sample-efficient-text-summarization-using-a | - | 17.74 | - |
| a-reinforced-topic-aware-convolutional | 31.15 | 10.85 | 27.68 |
| selective-encoding-for-abstractive-sentence | 29.21 | 9.56 | 25.51 |
| all-word-embeddings-from-one-embedding | 32.57 | 11.63 | 28.24 |
| ensure-the-correctness-of-the-summary | 29.33 | 10.24 | 25.24 |