OVERALL ACC: (BEFORE OUTPUT FORMATTER) 20 / 50 = 0.4 -------------------------------------------------------------------------------- OVERALL ACC: (AFTER OUTPUT FORMATTER) 23 / 50 = 0.46 Formatter Errors: [] -------------------------------------------------------------------------------- AGGREGATOR PERFORMANCE: EASY: 20 / 20 = 1.0 HARD: 0 / 9 = 0.0 -------------------------------------------------------------------------------- ANSWER MODULE STATS (WHEN CORRECTLY ACTIVATED ACCORDING TO THE DISPATCHER): ACC Single-Span-Extraction 9 / 22 = 0.4091 Single-Span-Multi-Hop-Extraction 10 / 22 = 0.4545 Multi-Spans-Extraction 0 / 9 = 0.0000 YesNo 4 / 7 = 0.5714 Arithmetic-Operations 0 / 0 = NaN Counting 0 / 0 = NaN Date-Duration 3 / 8 = 0.3750 Kinship 1 / 4 = 0.2500 -------------------------------------------------------------------------------- ANSWER MODULE STATS (WHEN WRONGLY ACTIVATED ACCORDING TO THE DISPATCHER): ACC Single-Span-Extraction 0 / 28 = 0.0000 Single-Span-Multi-Hop-Extraction 0 / 28 = 0.0000 Multi-Spans-Extraction 0 / 41 = 0.0000 YesNo 0 / 43 = 0.0000 Arithmetic-Operations 2 / 50 = 0.0400 Counting 0 / 50 = 0.0000 Date-Duration 11 / 42 = 0.2619 Kinship 0 / 46 = 0.0000 -------------------------------------------------------------------------------- ANSWER MODULE ERROR SAMPLES (WHEN CORRECTLY ACTIVATED): Single-Span-Extraction: ['D004Q05', 'D035Q06', 'D042Q07', 'D042Q12', 'D046Q07', 'D071Q11', 'D085Q02', 'D096Q03', 'D104Q01', 'D120Q03', 'D138Q09', 'D241Q04', 'D314Q03'] Single-Span-Multi-Hop-Extraction: ['D035Q06', 'D042Q12', 'D046Q07', 'D071Q11', 'D085Q02', 'D090Q01', 'D096Q03', 'D097Q03', 'D104Q01', 'D160Q04', 'D241Q04', 'D314Q03'] Multi-Spans-Extraction: ['D007Q01', 'D008Q06', 'D014Q03', 'D039Q03', 'D045Q02', 'D072Q07', 'D094Q04', 'D107Q01', 'D318Q04'] YesNo: ['D113Q04', 'D117Q08', 'D127Q05'] Arithmetic-Operations: [] Counting: [] Date-Duration: ['D042Q11', 'D082Q01', 'D104Q03', 'D215Q05', 'D243Q07'] Kinship: ['D040Q14', 'D040Q15', 'D091Q11'] --------------------------------------------------------------------------------