neleval significance
¶
Test for pairwise significance between systems
Usage summary¶
$ neleval significance --help
usage: neleval significance [-h] -g GOLD [-n TRIALS] [--permute] [--bootstrap]
[-j N_JOBS] [-f {json,none,tab}] [-m NAME]
[--type-weights FILE] [--metrics METRICS]
FILE [FILE ...]
Test for pairwise significance between systems
positional arguments:
FILE
optional arguments:
-h, --help show this help message and exit
-g GOLD, --gold GOLD
-n TRIALS, --trials TRIALS
--permute Use the approximate randomization method
--bootstrap Use bootstrap resampling
-j N_JOBS, --n_jobs N_JOBS
Number of parallel processes, use -1 for all CPUs
-f {json,none,tab}, --fmt {json,none,tab}
-m NAME, --measure NAME
Which measures to use: specify a name (or group name)
from the list-measures command. This flag may be
repeated.
--type-weights FILE File mapping gold and sys types to a weight, such as
produced by weights-for-hierarchy
--metrics METRICS Test significance for which metrics (default:
precision,recall,fscore)