Kg To Text Generation On Pathquestion
평가 지표
BLEU
METEOR
ROUGE
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | BLEU | METEOR | ROUGE | Paper Title | Repository |
|---|---|---|---|---|---|
| JointGT (BART) | 65.89 | 48.25 | 78.87 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs | |
| SOTA-NPT | 61.48 | 44.57 | 77.72 | Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks | |
| T5 | 58.95 | 44.72 | 76.58 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs | |
| BART | 63.74 | 47.23 | 77.76 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs | |
| JointGT (T5) | 60.45 | 45.38 | 77.59 | JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs |
0 of 5 row(s) selected.