Web Content Extraction on WCEB 1.0 (mid)
81.43ROUGE-N F1Dripper_fallback
Evaluation Results
| Method | Links | |
|---|---|---|
| Dripper_fallbackmode=Html+TEXT2025.11 | 81.43 | |
| Drippermode=Html+TEXT2025.11 | 80.05 | |
| Trafilaturamode=TEXT2025.11 | 77.85 | |
| Trafilaturamode=Html+TEXT2025.11 | 77.58 | |
| Readabilitymode=Html+TEXT2025.11 | 75.95 | |
| magic-htmlmode=Html+TEXT2025.11 | 75.73 | |
| Goose3mode=TEXT2025.11 | 73.12 | |
| news-pleasemode=TEXT2025.11 | 71.03 | |
| justTextmode=TEXT2025.11 | 69.66 | |
| BoilerPy3mode=TEXT2025.11 | 64.68 | |
| html2textmode=TEXT2025.11 | 61.65 | |
| BoilerPy3mode=Html+TEXT2025.11 | 60.35 | |
| GNEmode=Html+TEXT2025.11 | 50.69 | |
| ReaderLM-v2mode=TEXT2025.11 | 29.28 |