def main(train_loc,
model_loc,
train_oracle="static",
n_iter=15,
beam_width=1,
feat_thresh=10,
allow_reattach=False,
allow_reduce=False,
unlabelled=False,
n_sents=0,
seed=0):
random.seed(seed)
if beam_width >= 2:
parser = BeamParser(model_loc,
clean=True,
train_alg=train_oracle,
feat_thresh=feat_thresh,
allow_reduce=allow_reduce,
allow_reattach=allow_reattach,
beam_width=beam_width)
else:
parser = GreedyParser(model_loc,
clean=True,
train_alg=train_oracle,
feat_thresh=feat_thresh,
allow_reduce=allow_reduce,
allow_reattach=allow_reattach)
train_str = get_train_str(train_loc, n_sents)
train_data = redshift.io_parse.read_conll(train_str, unlabelled=unlabelled)
parser.train(train_data, n_iter=n_iter)
parser.save()
def wrapped(l1):
parser = redshift.parser.Parser(parser_dir, solver_type=solver_type,
clean=True, C=l1)
dev_gold = redshift.io_parse.read_conll(dev_loc.open().read())
train = redshift.io_parse.read_conll(train_loc.open().read())
parser.train(train)
dev = redshift.io_parse.read_pos(get_pos(dev_loc.open().read()))
acc = parser.add_parses(dev, gold=dev_gold) * 100
wrapped.models[l1] = acc
return acc
def main(train_loc, model_loc, train_oracle="static", n_iter=15, beam_width=1,
feat_thresh=10, allow_reattach=False, allow_reduce=False, unlabelled=False,
n_sents=0, seed=0):
random.seed(seed)
if beam_width >= 2:
parser = BeamParser(model_loc, clean=True,
train_alg=train_oracle,
feat_thresh=feat_thresh, allow_reduce=allow_reduce,
allow_reattach=allow_reattach, beam_width=beam_width)
else:
parser = GreedyParser(model_loc, clean=True, train_alg=train_oracle,
feat_thresh=feat_thresh,
allow_reduce=allow_reduce,
allow_reattach=allow_reattach)
train_str = get_train_str(train_loc, n_sents)
train_data = redshift.io_parse.read_conll(train_str, unlabelled=unlabelled)
parser.train(train_data, n_iter=n_iter)
parser.save()
