Skip to content

Commit 0da03ad

Browse files
authored
Merge pull request yzhangcs#52 from KoichiYasuoka/main
For UNK chars inside token
2 parents 3b16eec + 6b0909b commit 0da03ad

File tree

3 files changed

+6
-5
lines changed

3 files changed

+6
-5
lines changed

setup.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44

55
setup(
66
name='supar',
7-
version='1.0.0',
7+
version='1.0.0+dev20201223',
88
author='Yu Zhang',
99
author_email='yzhang.cs@outlook.com',
1010
description='Syntactic Parsing Models',
@@ -32,6 +32,6 @@
3232
'crf-constituency=supar.cmds.crf_constituency:main'
3333
]
3434
},
35-
python_requires='>=3.7',
35+
python_requires='>=3.6',
3636
zip_safe=False
3737
)

supar/cmds/cmd.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,8 @@ def parse(parser):
1313
parser.add_argument('--seed', '-s', default=1, type=int, help='seed for generating random numbers')
1414
parser.add_argument('--threads', '-t', default=16, type=int, help='max num of threads')
1515
parser.add_argument('--batch-size', default=5000, type=int, help='batch size')
16-
parser.add_argument("--local_rank", type=int, default=-1, help='node rank for distributed training')
16+
parser.add_argument('--local_rank', default=-1, type=int, help='node rank for distributed training')
17+
parser.add_argument('--epochs', default=5000, type=int, help='epochs')
1718
args, unknown = parser.parse_known_args()
1819
args, _ = parser.parse_known_args(unknown, args)
1920
args = Config(**vars(args))

supar/utils/field.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -318,8 +318,8 @@ def transform(self, sequences):
318318
if self.fix_len <= 0:
319319
self.fix_len = max(len(token) for seq in sequences for token in seq)
320320
if self.use_vocab:
321-
sequences = [[[self.vocab[i] for i in token] if token else [self.unk_index] for token in seq]
322-
for seq in sequences]
321+
sequences = [[[self.vocab[i] if i in self.vocab else self.unk_index for i in token] if token else [self.unk_index]
322+
for token in seq] for seq in sequences]
323323
if self.bos:
324324
sequences = [[[self.bos_index]] + seq for seq in sequences]
325325
if self.eos:

0 commit comments

Comments
 (0)