Merge pull request #422 from eryueniaobp/patch-1

use load_from_vocab_file
BrikerMan · Oct 21, 2020 · f92f5b2 · f92f5b2
2 parents 361fc11 + c33b0c8
commit f92f5b2
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/docs/embeddings/bert-embedding.rst b/docs/embeddings/bert-embedding.rst
@@ -37,7 +37,7 @@ Let's run a text classification model with BERT.
 
    bert_embedding = BertEmbedding('<PATH_TO_BERT_EMBEDDING>')
 
-   tokenizer = BertTokenizer(os.path.join('<PATH_TO_BERT_EMBEDDING>', 'vocab_chinese.txt'))
+   tokenizer = BertTokenizer.load_from_vocab_file(os.path.join('<PATH_TO_BERT_EMBEDDING>', 'vocab_chinese.txt'))
    sentences_tokenized = [tokenizer.tokenize(s) for s in sentences]
 
    """