diff --git a/PaddleNLP/dialogue_model_toolkit/auto_dialogue_evaluation/README.md b/PaddleNLP/dialogue_model_toolkit/auto_dialogue_evaluation/README.md
index 9ef563c7baa271a1a0c79c1a478affcbb36197ff..88e4eb64f218b8dc8c9eabca2fb2911f1c5c69d6 100644
--- a/PaddleNLP/dialogue_model_toolkit/auto_dialogue_evaluation/README.md
+++ b/PaddleNLP/dialogue_model_toolkit/auto_dialogue_evaluation/README.md
@@ -539,7 +539,7 @@ python -u main.py \
 ```
 
 ### 服务部署
-    模块内提供已训练好6个对话任务的inference_model模型，用户可根据自身业务情况进行下载使用。
+    模块内提供已训练好的5个inference_model模型，用户可根据自身业务情况进行下载使用。
 
 #### 服务器部署
     请参考PaddlePaddle官方提供的[服务器端部署](https://www.paddlepaddle.org.cn/documentation/docs/zh/1.5/advanced_usage/deploy/inference/index_cn.html)文档进行部署上线。
diff --git a/PaddleNLP/dialogue_model_toolkit/dialogue_general_understanding/dgu/reader.py b/PaddleNLP/dialogue_model_toolkit/dialogue_general_understanding/dgu/reader.py
index 56c58f0b56be712944366fe3a1c2edc0211e2c56..ba5bcc215cd14ab2b8f4814078215dd004368957 100644
--- a/PaddleNLP/dialogue_model_toolkit/dialogue_general_understanding/dgu/reader.py
+++ b/PaddleNLP/dialogue_model_toolkit/dialogue_general_understanding/dgu/reader.py
@@ -18,9 +18,8 @@ import sys
 import types
 import numpy as np
 
-sys.path.append("./dgu")
-import tokenization
-from batching import prepare_batch_data
+from dgu import tokenization
+from dgu.batching import prepare_batch_data
 
 
 class DataProcessor(object):