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

clean up tokenization spaces

Browse Source
This commit is contained in:
thomwolf
2019-02-04 17:41:22 +01:00
parent 850da1cc36
commit 6179f537a3
1 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
pytorch_pretrained_bert/tokenization_openai.py
View File

@@ -225,8 +225,14 @@ class OpenAIGPTTokenizer(object):
tokens.append(self.decoder[i]) tokens.append(self.decoder[i])
return tokens return tokens
def decode(self, ids, skip_special_tokens=False): def decode(self, ids, skip_special_tokens=False, clean_up_tokenization_spaces=False):
"""Converts a sequence of ids in a string.""" """Converts a sequence of ids in a string."""
tokens = self.convert_ids_to_tokens(ids, skip_special_tokens=skip_special_tokens) tokens = self.convert_ids_to_tokens(ids, skip_special_tokens=skip_special_tokens)
out_string = ''.join(tokens).replace('</w>', ' ').strip() out_string = ''.join(tokens).replace('</w>', ' ').strip()
if clean_up_tokenization_spaces:
out_string = out_string.replace('<unk>', '')
out_string = out_string.replace(' .', '.').replace(' ?', '?').replace(' !', '!').replace(' ,', ',').replace(' ,', ','
).replace(" n't", "n't").replace(" 'm", "'m").replace(" 're", "'re").replace(" do not", " don't"
).replace(" 's", "'s").replace(" t ", "'t ").replace(" s ", "'s ").replace(" m ", "'m "
).replace(" 've", "'ve")
return out_string return out_string