SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Tokenizers' encode function can output binary masks

Browse Source
This commit is contained in:
LysandreJik
2019-09-02 16:42:32 -04:00
parent 0d1dad6d53
commit e391d4735e
5 changed files with 39 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
pytorch_transformers/tokenization_bert.py
View File

@@ -194,14 +194,20 @@ class BertTokenizer(PreTrainedTokenizer):
"""
return [self.cls_token_id] + token_ids + [self.sep_token_id]
def add_special_tokens_sentences_pair(self, token_ids_0, token_ids_1):
def add_special_tokens_sentences_pair(self, token_ids_0, token_ids_1, output_mask=False):
"""
Adds special tokens to a sequence pair for sequence classification tasks.
A BERT sequence pair has the following format: [CLS] A [SEP] B [SEP]
"""
sep = [self.sep_token_id]
cls = [self.cls_token_id]
return cls + token_ids_0 + sep + token_ids_1 + sep
if output_mask:
return (
cls + token_ids_0 + sep + token_ids_1 + sep,
[0] * len(cls + token_ids_0 + sep) + [1] * len(token_ids_1 + sep)
)
else:
return cls + token_ids_0 + sep + token_ids_1 + sep
def save_vocabulary(self, vocab_path):
"""Save the tokenizer vocabulary to a directory or file."""