HyperAI超神経

Kg To Text Generation On Webquestions

評価指標

BLEU
METEOR
ROUGE

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

比較表
モデル名BLEUMETEORROUGE
jointgt-graph-text-joint-representation28.7830.5555.12
jointgt-graph-text-joint-representation29.6131.4855.42
toward-subgraph-guided-knowledge-graph29.4530.9655.45
jointgt-graph-text-joint-representation30.0232.0555.6
jointgt-graph-text-joint-representation28.9531.2954.47