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

Fix typo in example code

Browse Source 
Modify 'unambigiously' to 'unambiguously'
This commit is contained in:
Weixin Wang
2019-03-31 01:20:18 +08:00
committed by GitHub
parent ec5c1d6134
commit d07db28f52
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/run_classifier.py
View File

@@ -442,7 +442,7 @@ def convert_examples_to_features(examples, label_list, max_seq_length,
# sequence or the second sequence. The embedding vectors for `type=0` and # sequence or the second sequence. The embedding vectors for `type=0` and
# `type=1` were learned during pre-training and are added to the wordpiece # `type=1` were learned during pre-training and are added to the wordpiece
# embedding vector (and position vector). This is not *strictly* necessary # embedding vector (and position vector). This is not *strictly* necessary
# since the [SEP] token unambigiously separates the sequences, but it makes # since the [SEP] token unambiguously separates the sequences, but it makes
# it easier for the model to learn the concept of sequences. # it easier for the model to learn the concept of sequences.
# #
# For classification tasks, the first vector (corresponding to [CLS]) is # For classification tasks, the first vector (corresponding to [CLS]) is