Evaluate Interface¶
Note:Args that start with ‘--’ (eg. --save-config) can also be set in a config file (specified via --config). The config file uses YAML syntax and must represent a YAML ‘mapping’ (for details, see http://learn.getgrav.org/advanced/yaml). If an arg is specified in more than one place, then command line values override config file values which override defaults.
usage: kiwi evaluate [-h] [--type {probs,tags}] [--format {wmt17,wmt18}]
[--pred-format {wmt17,wmt18}] [--sents-avg {probs,tags}]
[--gold-sents GOLD_SENTS] [--gold-target GOLD_TARGET]
[--gold-source GOLD_SOURCE] [--gold-cal GOLD_CAL]
[--input-dir INPUT_DIR [INPUT_DIR ...]]
[--pred-sents PRED_SENTS [PRED_SENTS ...]]
[--pred-target PRED_TARGET [PRED_TARGET ...]]
[--pred-gaps PRED_GAPS [PRED_GAPS ...]]
[--pred-source PRED_SOURCE [PRED_SOURCE ...]]
[--pred-cal PRED_CAL]
Evaluation of WMT Quality Estimation¶
--type | Possible choices: probs, tags Input type for prediction file Default: “probs” |
--format | Possible choices: wmt17, wmt18 Input format for gold files Default: “wmt17” |
--pred-format | Possible choices: wmt17, wmt18 Input format for predicted files. Defaults to the same as –format. Default: “wmt18” |
--sents-avg | Possible choices: probs, tags Obtain scores for sentences by averaging over tags or probabilities. |
--gold-sents | Sentences gold standard. |
--gold-target | Target tags gold standard, or target and gaps if format == “wmt18”. |
--gold-source | Source tags gold standard. |
--gold-cal | Target Tags to calibrate. |
--input-dir | Directory with prediction files generated by predict pipeline. Setting this argument will evaluate all predictions for which a gold file is set. |
--pred-sents | Sentences HTER predictions. |
--pred-target | Target predictions; can be tags or probabilities (of BAD). See –type. |
--pred-gaps | Gap predictions; can be tags or probabilities (of BAD). (see –type). Use this option for files that only contain gap tags. |
--pred-source | Source predictions. can be tags or probabilities (of BAD). See –type. |
--pred-cal | Target Predictions to calibrate. |