Question Generation On Squad11
Metrics
BLEU-4
METEOR
ROUGE-L
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | BLEU-4 | METEOR | ROUGE-L |
|---|---|---|---|
| enhancing-pre-trained-models-with-text | 24.37 | 26.26 | 52.77 |
| unilmv2-pseudo-masked-language-models-for | 24.43 | - | - |
| ernie-gen-an-enhanced-multi-flow-pre-training | 25.41 | - | - |
| prophetnet-predicting-future-n-gram-for | 23.91 | 26.6 | 52.3 |
| learning-to-generate-questions-by-recovering | 23.7 | 25.9 | 52.3 |
| leveraging-context-information-for-natural | 13.91 | - | - |
| learning-to-generate-questions-by-recovering | 24.44 | 26.73 | 52.8 |
| evaluating-rewards-for-question-generation | 13.5 | - | - |
| unified-language-model-pre-training-for | 22.78 | 25.1 | 51.1 |
| neural-question-generation-from-text-a | 13.27 | - | - |
| textbox-2-0-a-text-generation-library-with | 25.08 | 26.73 | 52.55 |
| a-recurrent-bert-based-model-for-question | 22.17 | - | - |
| mixture-content-selection-for-diverse | 15.874 | - | - |