kiwi/assets/config/evaluate.yaml
gold_files:
source_tags: data/WMT20/sentence_level/en_de.nmt/dev.source_tags
target_tags: data/WMT20/sentence_level/en_de.nmt/dev.tags
sentence_scores: data/WMT20/sentence_level/en_de.nmt/dev.hter
# Two configuration options:
# 1. (Recommended) Pass the root folders where the predictions live,
# with the standard file names
predicted_dir:
# The evaluation pipeline supports evaluating multiple predictions at the same time
# by passing the folders as a list
- runs/0/4aa891368ff4402fa69a4b081ea2ba62
- runs/0/e9200ada6dc84bfea807b3b02b9c7212
# 2. Configure each predicted file separately
# predicted_files:
# source_tags:
# - runs/0/4aa891368ff4402fa69a4b081ea2ba62/source_tags
# - runs/0/e9200ada6dc84bfea807b3b02b9c7212/source_tags
# # (Recommended) Pass the predicted `targetgaps_tags` file as `target_tags`;
# # the target and gap tags will be separated and evaluated separately as well as jointly
# target_tags:
# - runs/0/4aa891368ff4402fa69a4b081ea2ba62/targetgaps_tags
# - runs/0/e9200ada6dc84bfea807b3b02b9c7212/targetgaps_tags
# # Alternatively:
# # target_tags:
# # - runs/0/4aa891368ff4402fa69a4b081ea2ba62/target_tags
# # - runs/0/e9200ada6dc84bfea807b3b02b9c7212/target_tags
# # gap_tags:
# # - runs/0/4aa891368ff4402fa69a4b081ea2ba62/gap_tags
# # - runs/0/e9200ada6dc84bfea807b3b02b9c7212/gap_tags
# sentence_scores:
# - runs/0/4aa891368ff4402fa69a4b081ea2ba62/sentence_scores
# - runs/0/e9200ada6dc84bfea807b3b02b9c7212/sentence_scores