MUC Performance Metric
Jump to navigation
Jump to search
See: MUC, Performance Metric, ACE Performance Metric.
References
- (NadSek, 2007) ⇒ David Nadeau, and Satoshi Sekine. (2007). “A Survey of Named Entity Recognition and Classification." Lingvisticae Investigationes. Volume 30, Edition 1.
- In MUC events (R. Grishman & Sundheim 1996, N. Chinchor 1999), a system is scored on two axes: its ability to find the correct type (TYPE) and its ability to find exact text (TEXT). A correct TYPE is credited if an entity is assigned the correct type, regardless of boundaries as long as there is an overlap. A correct TEXT is credited if entity boundaries are correct, regardless of the type. For both TYPE and TEXT, three measures are kept: the number of correct answers (COR), the number of actual system guesses (ACT) and the number of possible entities in the solution (POS).