Source Code Summarization On Deepcom Java
評価指標
BLEU-4
METEOR
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
モデル名 | BLEU-4 | METEOR | Paper Title | Repository |
|---|---|---|---|---|
| AdaMo-noise | 45.35 | 28.25% | Assemble Foundation Models for Automatic Code Summarization | |
| AdaMo-basic | 45.3 | 28.19% | Assemble Foundation Models for Automatic Code Summarization |
0 of 2 row(s) selected.