def main(linked_dir, labeled_out, score, core_weight, score_fes, debug, numerical):
"""
this script is the actual unsupervised approach which produces labeled data
out of entity linked sentences
"""
labeled = process_dir(linked_dir, score_fes, debug, numerical)
if score:
for sentence in labeled:
sentence['score'] = compute_score(sentence, score, core_weight)
if not score_fes:
[fe.pop('score') for fe in sentence['FEs']]
with codecs.open(labeled_out, 'wb', 'utf8') as f:
json.dump(labeled, f, ensure_ascii=False, indent=2)
def main(linked_dir, labeled_out, score, core_weight, score_fes, debug,
numerical):
"""
this script is the actual unsupervised approach which produces labeled data
out of entity linked sentences
"""
labeled = process_dir(linked_dir, score_fes, debug, numerical)
if score:
for sentence in labeled:
sentence['score'] = compute_score(sentence, score, core_weight)
if not score_fes:
[fe.pop('score') for fe in sentence['FEs']]
with codecs.open(labeled_out, 'wb', 'utf8') as f:
json.dump(labeled, f, ensure_ascii=False, indent=2)
def main(classified_output, output_file, id_to_title, triple_scores, \
format, sentence_score, core_weight, fe_score):
"""
serializes the classification result into triples
optionally scoring sentences and/or frame elements
"""
sentences = read_sentences(classified_output)
labeled = to_labeled(sentences, fe_score)
if sentence_score != 'nothing':
for sentence in labeled:
sentence['score'] = compute_score(sentence, sentence_score, core_weight)
mapping = json.load(id_to_title)
processed, discarded = to_assertions(labeled, mapping, output_file,
triple_scores, format)
def main(classified_output, output_file, id_to_title, triple_scores, \
format, sentence_score, core_weight, fe_score):
"""
serializes the classification result into triples
optionally scoring sentences and/or frame elements
"""
sentences = read_sentences(classified_output)
labeled = to_labeled(sentences, fe_score)
if sentence_score != 'nothing':
for sentence in labeled:
sentence['score'] = compute_score(sentence, sentence_score,
core_weight)
mapping = json.load(id_to_title)
processed, discarded = to_assertions(labeled, mapping, output_file,
triple_scores, format)
