diff --git a/demo/qa_classification/README.md b/demo/qa_classification/README.md
index 03e17a5781e6c10c30e3e25a9ace969b85cce6a3..a03baa25bd99f3d82178b826c6afcad7e9524055 100644
--- a/demo/qa_classification/README.md
+++ b/demo/qa_classification/README.md
@@ -65,7 +65,7 @@ reader = hub.reader.ClassifyReader(
 
 `hub.dataset.NLPCC_DBQA())` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录
 
-`module.get_vaocab_path()` 会返回预训练模型对应的词表
+`module.get_vocab_path()` 会返回预训练模型对应的词表
 
 `max_seq_len` 需要与Step1中context接口传入的序列长度保持一致