Files
Castor/kim_cnn/utils.py
Peng Shi 511f29a2a6 kim cnn with torchtext (#59)
* kim cnn with torchtext

* model

* import style
2017-10-05 09:38:07 -04:00

30 lines
938 B
Python

import re
def clean_str(string):
"""
Tokenization/string cleaning for all datasets except for SST.
"""
string = re.sub(r"[^A-Za-z0-9(),!?\'\`]", " ", string)
string = re.sub(r"\'s", " \'s", string)
string = re.sub(r"\'ve", " \'ve", string)
string = re.sub(r"n\'t", " n\'t", string)
string = re.sub(r"\'re", " \'re", string)
string = re.sub(r"\'d", " \'d", string)
string = re.sub(r"\'ll", " \'ll", string)
string = re.sub(r",", " , ", string)
string = re.sub(r"!", " ! ", string)
string = re.sub(r"\(", " ( ", string)
string = re.sub(r"\)", " ) ", string)
string = re.sub(r"\?", " ? ", string)
string = re.sub(r"\s{2,}", " ", string)
return string.lower().strip().split()
def clean_str_sst(string):
"""
Tokenization/string cleaning for the SST dataset
"""
string = re.sub(r"[^A-Za-z0-9(),!?\'\`]", " ", string)
string = re.sub(r"\s{2,}", " ", string)
return string.lower().strip().split()