Skip to content

fix problem about word level classification #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tabVersion wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix problem about word level classification #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0eb99f9
Update utils.py
tabVersion Aug 1, 2019
4413809
Update utils_fasttext.py
tabVersion Aug 1, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
from tqdm import tqdm
import time
from datetime import timedelta
import jieba


MAX_VOCAB_SIZE = 10000 # 词表长度限制
Expand All @@ -30,7 +31,7 @@ def build_vocab(file_path, tokenizer, max_size, min_freq):

def build_dataset(config, ues_word):
if ues_word:
tokenizer = lambda x: x.split(' ') # 以空格隔开，word-level
tokenizer = lambda x: list(jieba.cut(x))
else:
tokenizer = lambda x: [y for y in x] # char-level
if os.path.exists(config.vocab_path):
Expand Down
3 changes: 2 additions & 1 deletion utils_fasttext.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
from tqdm import tqdm
import time
from datetime import timedelta
import jieba


MAX_VOCAB_SIZE = 10000
Expand All @@ -30,7 +31,7 @@ def build_vocab(file_path, tokenizer, max_size, min_freq):

def build_dataset(config, ues_word):
if ues_word:
tokenizer = lambda x: x.split(' ') # 以空格隔开，word-level
tokenizer = lambda x: list(jieba.cut(x))
else:
tokenizer = lambda x: [y for y in x] # char-level
if os.path.exists(config.vocab_path):
Expand Down