Text Summarization On Wikihow
評価指標
ROUGE-1
ROUGE-2
ROUGE-L
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 | ROUGE-1 | ROUGE-2 | ROUGE-L | Paper Title | Repository |
|---|---|---|---|---|---|
| Pointer-generator + coverage | 28.53 | 9.23 | 26.54 | WikiHow: A Large Scale Text Summarization Dataset | |
| BertSum | 35.91 | 13.9 | 34.82 | Abstractive Summarization of Spoken andWritten Instructions with BERT | |
| MatchSum (BERT-base) | 31.85 | 8.98 | 29.58 | Extractive Summarization as Text Matching |
0 of 3 row(s) selected.