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

Sentence -> Sequence. Removed output_mask from the special token addition methods.

Browse Source
This commit is contained in:
LysandreJik
2019-09-19 09:55:36 +02:00
parent 8cba057260
commit bf503158c5
13 changed files with 49 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
pytorch_transformers/tokenization_xlm.py
View File

@@ -754,28 +754,21 @@ class XLMTokenizer(PreTrainedTokenizer):
out_string = ''.join(tokens).replace('</w>', ' ').strip()
return out_string
def add_special_tokens_single_sentence(self, token_ids):
def add_special_tokens_single_sequence(self, token_ids):
"""
Adds special tokens to a sequence for sequence classification tasks.
An XLM sequence has the following format: [CLS] X [SEP]
"""
return [self.cls_token_id] + token_ids + [self.sep_token_id]
def add_special_tokens_sentences_pair(self, token_ids_0, token_ids_1, output_mask=False):
def add_special_tokens_sequence_pair(self, token_ids_0, token_ids_1):
"""
Adds special tokens to a sequence pair for sequence classification tasks.
An XLM sequence pair has the following format: [CLS] A [SEP] B [SEP]
"""
sep = [self.sep_token_id]
cls = [self.cls_token_id]
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
return cls + token_ids_0 + sep + token_ids_1 + sep
def save_vocabulary(self, save_directory):
"""Save the tokenizer vocabulary and merge files to a directory."""