diff --git a/demo/senta/README.md b/demo/senta/README.md
index ffafc02192d00b7470bf1a62151913eb346e7e4e..ff61224fd5a31f2e17d4f888b28ec2af59c47db5 100644
--- a/demo/senta/README.md
+++ b/demo/senta/README.md
@@ -1,10 +1,10 @@
-# senta
+# PaddleHub Senta
 
 ## 关于
 
-本示例展示如何使用senta Module进行预测。
+本示例展示如何使用PaddleHub Senta Module进行预测。
 
-senta是中文情感分析模型，可以用于进行中文句子的情感分析，输出结果为`{正向/中性/负向}`中的一个，关于模型的训练细节，请查看[senta](https://github.com/baidu/senta)
+Senta是百度NLP开放的中文情感分析模型，可以用于进行中文句子的情感分析，输出结果为`{正向/中性/负向}`中的一个，关于模型的结构细节，请查看[Senta](https://github.com/baidu/senta), 本示例代码选择的是Senta-BiLSTM模型。
 
 ## 准备工作
 
@@ -27,18 +27,25 @@ $ pip install --upgrade paddlepaddle
 
 ## 命令行方式预测
 
-`infer.sh`给出了使用命令行调用Module预测的示例脚本
-通过以下命令试验下效果
+`cli_demo.sh`给出了使用命令行接口 (Command Line Interface) 调用Module预测的示例脚本
+通过以下命令体验下效果
 
 ```shell
-$ sh infer.sh
+$ sh cli_demo.sh
 ```
 
 ## 通过python API预测
 
-`infer_by_code.py`给出了使用python API调用Module预测的示例代码
+`senta_demo.py`给出了使用python API调用Module预测的示例代码
 通过以下命令试验下效果
 
 ```shell
-python infer_by_code.py
+python senta_demo.py
+```
+
+## 通过PaddleHub Finetune API微调
+`senta_finetune.py` 给出了如何使用Senta模型的句子特征进行Fine-tuning的实例代码。
+可以运行以下命令在ChnSentiCorp数据集上进行Fine-tuning.
+```shell
+$ sh run_finetune.sh
 ```
diff --git a/demo/senta/infer.sh b/demo/senta/cli_demo.sh
similarity index 100%
rename from demo/senta/infer.sh
rename to demo/senta/cli_demo.sh
diff --git a/demo/senta/infer_by_code.py b/demo/senta/infer_by_code.py
deleted file mode 100644
index 1033bb7d9189603f5a3dd1acc26aafee71813944..0000000000000000000000000000000000000000
--- a/demo/senta/infer_by_code.py
+++ /dev/null
@@ -1,46 +0,0 @@
-import os
-import paddlehub as hub
-
-
-def infer_with_input_text():
-    # get senta module
-    senta = hub.Module(name="senta")
-
-    test_text = ["这家餐厅很好吃", "这部电影真的很差劲"]
-
-    # get the input keys for signature 'sentiment_classify'
-    data_format = senta.processor.data_format(sign_name='sentiment_classify')
-    key = list(data_format.keys())[0]
-
-    # set input dict
-    input_dict = {key: test_text}
-
-    # execute predict and print the result
-    results = senta.sentiment_classify(data=input_dict)
-    for index, result in enumerate(results):
-        hub.logger.info("sentence %d segmented result: %s" %
-                        (index + 1, result['sentiment_key']))
-
-
-def infer_with_input_file():
-    # get senta module
-    senta = hub.Module(name="senta")
-
-    # get the input keys for signature 'sentiment_classify'
-    data_format = senta.processor.data_format(sign_name='sentiment_classify')
-    key = list(data_format.keys())[0]
-
-    # parse input file
-    test_file = os.path.join("test", "test.txt")
-    test_text = hub.io.parser.txt_parser.parse(test_file)
-
-    # set input dict
-    input_dict = {key: test_text}
-    results = senta.sentiment_classify(data=input_dict)
-    for index, result in enumerate(results):
-        hub.logger.info("sentence %d segmented result: %s" %
-                        (index + 1, result['sentiment_key']))
-
-
-if __name__ == "__main__":
-    infer_with_input_text()
diff --git a/demo/senta/run_classifier.sh b/demo/senta/run_finetune.sh
similarity index 60%
rename from demo/senta/run_classifier.sh
rename to demo/senta/run_finetune.sh
index 5fd33cf014d4d4a230a9f6c46fc0a4bb18dfdd9c..77361f696ebff07ff6f6f756a4b20fb9f35f3633 100644
--- a/demo/senta/run_classifier.sh
+++ b/demo/senta/run_finetune.sh
@@ -1,11 +1,10 @@
 export CUDA_VISIBLE_DEVICES=0
 
-# User can select chnsenticorp, nlpcc_dbqa, lcqmc for different task
 DATASET="chnsenticorp"
 CKPT_DIR="./ckpt_${DATASET}"
 
-python -u text_classifier.py \
+python -u senta_finetune.py \
                    --batch_size=24 \
                    --use_gpu=False \
                    --checkpoint_dir=${CKPT_DIR} \
-                   --num_epoch=10
+                   --num_epoch=3
diff --git a/demo/senta/senta_demo.py b/demo/senta/senta_demo.py
new file mode 100644
index 0000000000000000000000000000000000000000..c23bc5300dc78d6012d000fc3fc89ed845acfd8a
--- /dev/null
+++ b/demo/senta/senta_demo.py
@@ -0,0 +1,15 @@
+# coding: utf-8
+import os
+import paddlehub as hub
+
+if __name__ == "__main__":
+    # Load Senta-BiLSTM module
+    senta = hub.Module(name="senta")
+
+    test_text = ["这家餐厅很好吃", "这部电影真的很差劲"]
+
+    input_dict = {"text": test_text}
+
+    results = senta.sentiment_classify(data=input_dict)
+    for index, result in enumerate(results):
+        print(test_text[index], result['sentiment_key'])
diff --git a/demo/senta/text_classifier.py b/demo/senta/senta_finetune.py
similarity index 100%
rename from demo/senta/text_classifier.py
rename to demo/senta/senta_finetune.py
diff --git a/demo/senta/test/test.txt b/demo/senta/test/test.txt
index 80c4e030fa95c22e19688e7030e7b682c006ba09..8ac5c8dfe0125b2249b0e8162b5a6e4d5e97601b 100644
--- a/demo/senta/test/test.txt
+++ b/demo/senta/test/test.txt
@@ -1,2 +1,2 @@
-这部电影真的很赞
-售后太差！
+这家餐厅很好吃
+这部电影真的很差劲