====================================================
TAC KBP 2016 SPANISH SLOT FILLING EVALUATION RESULTS
====================================================


Team ID:  RPI_BLENDER
Organization:  Rensselaer Polytechnic Institute


*************************************************************

Run ID:  RPI_BLENDER_SF_SPA_1
Did the run access the live Web during the evaluation window:  No
Did the run extract relations from the Cold Start source corpus: Yes
Did the run generate meaningful confidence values: Yes

Slot Filling Evaluation:

Metric                   RunID                Hop Prec   Recall F1    
SF-ALL-Micro             RPI_BLENDER_SF_SPA_1 0   0.2381 0.0151 0.0283
SF-ALL-Micro             RPI_BLENDER_SF_SPA_1 1   0.0000 0.0000 0.0000
SF-ALL-Micro             RPI_BLENDER_SF_SPA_1 ALL 0.2381 0.0092 0.0177
SF-ALL-Macro             RPI_BLENDER_SF_SPA_1 0   0.0232 0.0258 0.0241
SF-ALL-Macro             RPI_BLENDER_SF_SPA_1 1   0.0000 0.0000 0.0000
SF-ALL-Macro             RPI_BLENDER_SF_SPA_1 ALL 0.0155 0.0172 0.0160
LDC-MAX-ALL-Micro        RPI_BLENDER_SF_SPA_1 0   0.2143 0.0120 0.0228
LDC-MAX-ALL-Micro        RPI_BLENDER_SF_SPA_1 1   0.0000 0.0000 0.0000
LDC-MAX-ALL-Micro        RPI_BLENDER_SF_SPA_1 ALL 0.2143 0.0080 0.0154
LDC-MAX-ALL-Macro        RPI_BLENDER_SF_SPA_1 0   0.0180 0.0216 0.0192
LDC-MAX-ALL-Macro        RPI_BLENDER_SF_SPA_1 1   0.0000 0.0000 0.0000
LDC-MAX-ALL-Macro        RPI_BLENDER_SF_SPA_1 ALL 0.0121 0.0145 0.0129
LDC-MEAN-ALL-Macro       RPI_BLENDER_SF_SPA_1 0   0.0180 0.0216 0.0192
LDC-MEAN-ALL-Macro       RPI_BLENDER_SF_SPA_1 1   0.0000 0.0000 0.0000
LDC-MEAN-ALL-Macro       RPI_BLENDER_SF_SPA_1 ALL 0.0121 0.0145 0.0129

*ALL-Macro Prec, Recall and F1 refer to mean-precision, mean-recall and mean-F1.

NIL-DETECTION P/R/F1:				0.3103 0.9837 0.4718