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


Team ID:  LDC
Organization:  Linguistic Data Consortium


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

Run ID:  LDC_SF_ENG_1
Did the run access the live Web during the evaluation window:  Yes
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             LDC_SF_ENG_1 0   0.8283 0.3733 0.5146
SF-ALL-Micro             LDC_SF_ENG_1 1   0.7429 0.2549 0.3796
SF-ALL-Micro             LDC_SF_ENG_1 ALL 0.8044 0.3333 0.4713
SF-ALL-Macro             LDC_SF_ENG_1 0   0.7421 0.6001 0.6330
SF-ALL-Macro             LDC_SF_ENG_1 1   0.3543 0.3059 0.3149
SF-ALL-Macro             LDC_SF_ENG_1 ALL 0.5948 0.4883 0.5122
LDC-MAX-ALL-Micro        LDC_SF_ENG_1 0   0.8132 0.3415 0.4810
LDC-MAX-ALL-Micro        LDC_SF_ENG_1 1   0.7704 0.3377 0.4695
LDC-MAX-ALL-Micro        LDC_SF_ENG_1 ALL 0.7985 0.3402 0.4771
LDC-MAX-ALL-Macro        LDC_SF_ENG_1 0   0.7098 0.5741 0.6043
LDC-MAX-ALL-Macro        LDC_SF_ENG_1 1   0.4748 0.4099 0.4220
LDC-MAX-ALL-Macro        LDC_SF_ENG_1 ALL 0.6175 0.5096 0.5327
LDC-MEAN-ALL-Macro       LDC_SF_ENG_1 0   0.7098 0.5741 0.6043
LDC-MEAN-ALL-Macro       LDC_SF_ENG_1 1   0.3848 0.3373 0.3455
LDC-MEAN-ALL-Macro       LDC_SF_ENG_1 ALL 0.5822 0.4811 0.5027

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

NIL-DETECTION P/R/F1:				0.2921 0.9024 0.4413