Web Content Extraction on WCEB 1.0 (all)
81.54ROUGE-N F1Dripper_fallback
Evaluation Results
| Method | Links | |
|---|---|---|
| Dripper_fallbackmode=Html+TEXT2025.11 | 81.54 | |
| Drippermode=Html+TEXT2025.11 | 80.02 | |
| Trafilaturamode=TEXT2025.11 | 78.33 | |
| Trafilaturamode=Html+TEXT2025.11 | 77.91 | |
| Readabilitymode=Html+TEXT2025.11 | 76.42 | |
| magic-htmlmode=Html+TEXT2025.11 | 75.06 | |
| Goose3mode=TEXT2025.11 | 72.72 | |
| news-pleasemode=TEXT2025.11 | 70.48 | |
| justTextmode=TEXT2025.11 | 69.36 | |
| BoilerPy3mode=TEXT2025.11 | 62.21 | |
| html2textmode=TEXT2025.11 | 61.42 | |
| BoilerPy3mode=Html+TEXT2025.11 | 60.15 | |
| GNEmode=Html+TEXT2025.11 | 51.66 | |
| ReaderLM-v2mode=TEXT2025.11 | 30.77 |