def __init__(
self,
parser_model=None,
reranker_features=None,
reranker_weights=None,
parser_options=None,
reranker_options=None,
):
"""
Load a BLLIP Parser model from scratch. You'll typically want to
use the ``from_unified_model_dir()`` class method to construct
this object.
:param parser_model: Path to parser model directory
:type parser_model: str
:param reranker_features: Path the reranker model's features file
:type reranker_features: str
:param reranker_weights: Path the reranker model's weights file
:type reranker_weights: str
:param parser_options: optional dictionary of parser options, see
``bllipparser.RerankingParser.RerankingParser.load_parser_options()``
for more information.
:type parser_options: dict(str)
:param reranker_options: optional
dictionary of reranker options, see
``bllipparser.RerankingParser.RerankingParser.load_reranker_model()``
for more information.
:type reranker_options: dict(str)
"""
_ensure_bllip_import_or_error()
parser_options = parser_options or {}
reranker_options = reranker_options or {}
self.rrp = RerankingParser()
self.rrp.load_parser_model(parser_model, **parser_options)
if reranker_features and reranker_weights:
self.rrp.load_reranker_model(
features_filename=reranker_features,
weights_filename=reranker_weights,
**reranker_options
)
break
if good:
new_nbest.append(t)
return new_nbest
if __name__ == '__main__':
if len(sys.argv) != 3 and len(sys.argv) != 4:
print('usage: python traversal.py vocab.gz gold.gz [nbest.gz]')
sys.exit(0)
words = read_vocab(sys.argv[1])
if len(sys.argv) == 3:
for line in open_file(sys.argv[2]):
print(ptb(line[:-1], words))
else:
rrp = RerankingParser()
parser = 'wsj/WSJ-PTB3/parser'
rrp.load_parser_model(parser)
for gold, nbest in zip(open_file(sys.argv[2]),
generate_nbest(open_file(sys.argv[3]))):
for tree in nbest:
tree['seq'] = ptb(tree['ptb'], words)
nbest = remove_duplicates(nbest)
gold = Tree(gold)
print(len(nbest))
for t in nbest:
scores = Tree(t['ptb']).evaluate(gold)
print(scores['gold'], scores['test'], scores['matched'])
print(t['seq'])
