2,150
edits
GATE track 1 session: Difference between revisions
Jump to navigation
Jump to search
→Evaluation / Metrics
| Line 35: | Line 35: | ||
* Evaluation metric - mathematically against human annotated | * Evaluation metric - mathematically against human annotated | ||
* Scoring - performance measures for annotation types | * Scoring - performance measures for annotation types | ||
* Precision = correct / correct + spurious | |||
* Recall = correct / correct + missing | |||
* F-measure is precision and recall (harmonic mean) | |||
* F=2⋅(precision⋅recall / precision+recall) | |||
* GATE supports average, strict, lenient | |||
* Result types - Correct, missing, spurious, partially correct (overlapped) | * Result types - Correct, missing, spurious, partially correct (overlapped) | ||