if __name__ == '__main__':
import argparse
from stog.data.dataset_readers.amr_parsing.io import AMRIO
parser = argparse.ArgumentParser('feature_annotator.py')
parser.add_argument('files', nargs='+', help='files to annotate.')
parser.add_argument('--compound_file', default='')
args = parser.parse_args()
annotator = FeatureAnnotator('http://localhost:9000', args.compound_file)
for file_path in args.files:
logger.info('Processing {}'.format(file_path))
for i, amr in enumerate(AMRIO.read(file_path), 1):
if i % 1000 == 0:
logger.info('{} processed.'.format(i))
annotation = annotator(amr.sentence)
amr.tokens = annotation['tokens']
amr.lemmas = annotation['lemmas']
amr.pos_tags = annotation['pos_tags']
amr.ner_tags = annotation['ner_tags']
amr.original = annotation['original']
with open(file_path + '.features', 'a', encoding='utf-8') as f:
AMRIO.dump([amr], f)
logger.info('Done!')
def dump_amr_features(amr, annotation, f):
amr.tokens = annotation['tokens']
amr.lemmas = annotation['lemmas']
amr.pos_tags = annotation['pos_tags']
amr.ner_tags = annotation['ner_tags']
AMRIO.dump([amr], f)
