def retrieve_gold_standard(pipeline_options, is_wmt18_format):
golds = {}
if pipeline_options.gold_target:
gold_target = _wmt_to_labels(read_file(pipeline_options.gold_target))
if is_wmt18_format:
gold_target, gold_gaps = _split_wmt18(gold_target)
golds[const.GAP_TAGS] = gold_gaps
golds[const.TARGET_TAGS] = gold_target
# handling of gold source
if pipeline_options.gold_source:
gold_source = _wmt_to_labels(read_file(pipeline_options.gold_source))
golds[const.SOURCE_TAGS] = gold_source
# handling of gold sentences
if pipeline_options.gold_sents:
gold_sentences = _read_sentence_scores(pipeline_options.gold_sents)
golds[const.SENTENCE_SCORES] = gold_sentences
return golds
def retrieve_predictions(pipeline_options, is_wmt18_pred_format):
pred_files = {target: [] for target in const.TARGETS}
if pipeline_options.pred_target:
for pred_file in pipeline_options.pred_target:
pred_target = read_file(pred_file)
if is_wmt18_pred_format:
pred_target, pred_gaps = _split_wmt18(pred_target)
pred_files[const.GAP_TAGS].append((str(pred_file), pred_gaps))
pred_files[const.TARGET_TAGS].append((str(pred_file), pred_target))
if pipeline_options.pred_gaps:
for pred_file in pipeline_options.pred_gaps:
pred_gaps = read_file(pred_file)
pred_files[const.GAP_TAGS].append((str(pred_file), pred_gaps))
if pipeline_options.pred_source:
for pred_file in pipeline_options.pred_source:
pred_source = read_file(pred_file)
pred_files[const.SOURCE_TAGS].append((str(pred_file), pred_source))
if pipeline_options.pred_sents:
for pred_file in pipeline_options.pred_sents:
pred_sents = _read_sentence_scores(pred_file)
pred_files[const.SENTENCE_SCORES].append(
(str(pred_file), pred_sents))
if pipeline_options.input_dir:
for input_dir in pipeline_options.input_dir:
input_dir = Path(input_dir)
for target in const.TAGS:
pred_file = input_dir.joinpath(target)
if pred_file.exists() and pred_file.is_file():
pred_files[pred_file.name].append(
(str(pred_file), read_file(pred_file)))
for target in [const.SENTENCE_SCORES, const.BINARY]:
pred_file = input_dir.joinpath(target)
if pred_file.exists() and pred_file.is_file():
pred_files[pred_file.name].append(
(str(pred_file),
_read_sentence_scores(str(pred_file))))
# Numericalize Text Labels
if pipeline_options.type == "tags":
for tag_name in const.TAGS:
for i in range(len(pred_files[tag_name])):
fname, pred_tags = pred_files[tag_name][i]
pred_files[tag_name][i] = (fname, _wmt_to_labels(pred_tags))
return pred_files