OVERALL ACC: (BEFORE OUTPUT FORMATTER) 119 / 193 = 0.616580310880829 -------------------------------------------------------------------------------- OVERALL ACC: (AFTER OUTPUT FORMATTER) 121 / 193 = 0.6269430051813472 Formatter Errors: ['D285Q04'] -------------------------------------------------------------------------------- AGGREGATOR PERFORMANCE: EASY: 119 / 121 = 0.9834710743801653 HARD: 0 / 23 = 0.0 -------------------------------------------------------------------------------- DISPATCHER AMODE TOP-3 PERFORMANCE: (COVERAGE) 183 / 190 = 0.9631578947368421 ERRORS: ['D039Q03', 'D039Q04', 'D039Q05', 'D039Q06', 'D117Q01', 'D117Q03', 'D117Q06'] -------------------------------------------------------------------------------- DISPATCHER ATYPE-3 PERFORMANCE: (COVERAGE) 182 / 190 = 0.9578947368421052 ERRORS: ['D117Q03', 'D117Q04', 'D117Q06', 'D291Q09', 'D309Q04', 'D309Q05', 'D315Q04', 'D315Q09'] -------------------------------------------------------------------------------- ANSWER MODULE STATS (WHEN CORRECTLY ACTIVATED ACCORDING TO THE DISPATCHER): ACC Single-Span-Extraction 58 / 97 = 0.5979 Single-Span-Multi-Hop-Extraction 65 / 97 = 0.6701 Multi-Spans-Extraction 2 / 20 = 0.1000 YesNo 18 / 25 = 0.7200 Arithmetic-Operations 9 / 14 = 0.6429 Counting 0 / 0 = NaN Date-Duration 18 / 32 = 0.5625 Kinship 0 / 2 = 0.0000 Wiki-Json-Inference 0 / 0 = NaN Summarize 0 / 0 = NaN -------------------------------------------------------------------------------- ANSWER MODULE STATS (WHEN WRONGLY ACTIVATED ACCORDING TO THE DISPATCHER): ACC Single-Span-Extraction 20 / 96 = 0.2083 Single-Span-Multi-Hop-Extraction 22 / 96 = 0.2292 Multi-Spans-Extraction 16 / 173 = 0.0925 YesNo 0 / 168 = 0.0000 Arithmetic-Operations 2 / 179 = 0.0112 Counting 0 / 0 = NaN Date-Duration 4 / 161 = 0.0248 Kinship 5 / 191 = 0.0262 Wiki-Json-Inference 0 / 0 = NaN Summarize 0 / 190 = 0.0000 -------------------------------------------------------------------------------- ANSWER MODULE ERRORS (WHEN CORRECTLY ACTIVATED): Single-Span-Extraction: ['D009Q02', 'D033Q01', 'D033Q02', 'D033Q03', 'D033Q04', 'D033Q05', 'D033Q06', 'D033Q07', 'D033Q08', 'D033Q12', 'D033Q14', 'D039Q03', 'D039Q04', 'D039Q05', 'D039Q06', 'D069Q12', 'D087Q06', 'D093Q07', 'D105Q06', 'D105Q07', 'D105Q08', 'D249Q03', 'D249Q04', 'D249Q06', 'D255Q06', 'D255Q08', 'D255Q09', 'D255Q12', 'D255Q13', 'D261Q07', 'D267Q02', 'D273Q01', 'D291Q08', 'D291Q09', 'D303Q03', 'D309Q04', 'D315Q03', 'D315Q07', 'D315Q09'] Single-Span-Multi-Hop-Extraction: ['D003Q04', 'D009Q02', 'D033Q01', 'D033Q03', 'D033Q04', 'D033Q05', 'D033Q06', 'D033Q07', 'D033Q08', 'D033Q14', 'D033Q15', 'D039Q03', 'D039Q04', 'D039Q05', 'D039Q06', 'D039Q08', 'D039Q09', 'D045Q04', 'D069Q03', 'D069Q09', 'D069Q12', 'D087Q01', 'D087Q06', 'D093Q07', 'D243Q04', 'D255Q04', 'D255Q10', 'D255Q12', 'D291Q09', 'D303Q03', 'D315Q01', 'D315Q09'] Multi-Spans-Extraction: ['D003Q03', 'D003Q06', 'D009Q04', 'D015Q02', 'D015Q04', 'D033Q09', 'D033Q10', 'D045Q02', 'D087Q03', 'D087Q04', 'D093Q04', 'D105Q05', 'D117Q04', 'D249Q02', 'D303Q06', 'D309Q05', 'D315Q02', 'D315Q04'] YesNo: ['D069Q11', 'D117Q08', 'D201Q05', 'D255Q07', 'D291Q03', 'D291Q05', 'D315Q06'] Arithmetic-Operations: ['D015Q05', 'D015Q06', 'D069Q13', 'D183Q02', 'D309Q02'] Counting: [] Date-Duration: ['D033Q11', 'D069Q04', 'D069Q05', 'D069Q06', 'D069Q07', 'D087Q02', 'D105Q02', 'D105Q04', 'D117Q01', 'D117Q02', 'D243Q07', 'D255Q01', 'D267Q07', 'D303Q05'] Kinship: ['D039Q01', 'D039Q02'] Wiki-Json-Inference: [] Summarize: [] --------------------------------------------------------------------------------