Source code for kiwi.cli.pipelines.evaluate

#  OpenKiwi: Open-Source Machine Translation Quality Estimation
#  Copyright (C) 2019 Unbabel <openkiwi@unbabel.com>
#
#  This program is free software: you can redistribute it and/or modify
#  it under the terms of the GNU Affero General Public License as published
#  by the Free Software Foundation, either version 3 of the License, or
#  (at your option) any later version.
#
#  This program is distributed in the hope that it will be useful,
#  but WITHOUT ANY WARRANTY; without even the implied warranty of
#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#  GNU Affero General Public License for more details.
#
#  You should have received a copy of the GNU Affero General Public License
#  along with this program.  If not, see <https://www.gnu.org/licenses/>.
#

import logging

from kiwi.cli.better_argparse import PipelineParser
from kiwi.cli.opts import PathType
from kiwi.lib import evaluate

logger = logging.getLogger(__name__)


[docs]def evaluate_opts(parser): # Evaluation options group = parser.add_argument_group("Evaluation of WMT Quality Estimation") group.add_argument( "--type", help="Input type for prediction file", choices=["probs", "tags"], type=str, default="probs", ) group.add_argument( "--format", help="Input format for gold files", choices=["wmt17", "wmt18"], type=str, default="wmt17", ) group.add_argument( "--pred-format", help="Input format for predicted files. Defaults to the same as " "--format.", choices=["wmt17", "wmt18"], type=str, default="wmt18", ) group.add_argument( "--sents-avg", help="Obtain scores for sentences by averaging over tags or " "probabilities.", choices=["probs", "tags"], type=str, # default=None ) # Gold files. group.add_argument( "--gold-sents", help="Sentences gold standard. ", type=PathType(exists=True), required=False, ) group.add_argument( "--gold-target", help="Target tags gold standard, or target and gaps " 'if format == "wmt18".', type=PathType(exists=True), required=False, ) group.add_argument( "--gold-source", help="Source tags gold standard.", type=PathType(exists=True), required=False, ) group.add_argument( "--gold-cal", help="Target Tags to calibrate.", type=PathType(exists=True), required=False, ) # Prediction Files group.add_argument( "--input-dir", help="Directory with prediction files generated by predict pipeline. " "Setting this argument will evaluate all predictions for " "which a gold file is set.", nargs="+", type=PathType(exists=True), # required=True ) group.add_argument( "--pred-sents", help="Sentences HTER predictions.", type=PathType(exists=True), nargs="+", required=False, ) group.add_argument( "--pred-target", help="Target predictions; can be tags or probabilities (of BAD). " "See --type.", type=PathType(exists=True), nargs="+", required=False, ) group.add_argument( "--pred-gaps", help="Gap predictions; can be tags or probabilities (of BAD). " "(see --type). Use this option for files that only contain gap " "tags.", type=PathType(exists=True), nargs="+", required=False, ) group.add_argument( "--pred-source", help="Source predictions. can be tags or probabilities (of BAD). " " See --type.", type=PathType(exists=True), nargs="+", required=False, ) group.add_argument( "--pred-cal", help="Target Predictions to calibrate.", type=PathType(exists=True), required=False, )
[docs]def build_parser(): return PipelineParser( name="evaluate", model_parsers=None, options_fn=evaluate_opts, add_io_options=True, add_general_options=False, add_logging_options=False, add_save_load_options=False, )
[docs]def main(argv=None): parser = build_parser() options = parser.parse(args=argv) evaluate.evaluate_from_options(options)
if __name__ == "__main__": main()