From f2b8303f9f0bb0b0ca2900553409203d37b7cc37 Mon Sep 17 00:00:00 2001
From: Superjom <superjom@gmail.com>
Date: Wed, 12 Jul 2017 20:59:23 +0800
Subject: [PATCH] change demo datasets

---
 dssm/README.md                     | 6 ++----
 dssm/data/classification/test.txt  | 4 ++--
 dssm/data/classification/train.txt | 2 +-
 dssm/data/rank/test.txt            | 2 +-
 dssm/data/rank/train.txt           | 2 +-
 5 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/dssm/README.md b/dssm/README.md
index 9b1e17e1..6bf74006 100644
--- a/dssm/README.md
+++ b/dssm/README.md
@@ -101,7 +101,7 @@ DSSM模型可以拆成三小块实现，分别是左边和右边的DNN，以及
 
 下面是各个部分具体的实现方法，所有的代码均包含在 `./network_conf.py` 中。
 
-### 创建文本的embedding
+### 创建文本的词向量表
 ```python
 def create_embedding(self, input, prefix=''):
     '''
@@ -129,7 +129,6 @@ def create_cnn(self, emb, prefix=''):
     @prefix: str
         prefix of layers' names, used to share parameters between more than one `cnn` parts.
     '''
-
     def create_conv(context_len, hidden_size, prefix):
         key = "%s_%d_%d" % (prefix, context_len, hidden_size)
         conv = paddle.networks.sequence_conv_pool(
@@ -147,7 +146,6 @@ def create_cnn(self, emb, prefix=''):
     conv_3 = create_conv(3, self.dnn_dims[1], "cnn")
     logger.info('create a sequence_conv_pool which context width is 4')
     conv_4 = create_conv(4, self.dnn_dims[1], "cnn")
-
     return conv_3, conv_4
 ```
 
@@ -267,7 +265,7 @@ def _build_classification_or_regression_model(self, is_classification):
     return cost, prediction, label
 ```
 ### Pairwise Rank实现
-Pairwise Rank复用上面的DNN结构，同一个source对两个target求相似度打分，使用了hinge lost，
+Pairwise Rank复用上面的DNN结构，同一个source对两个target求相似度打分，
 如果左边的target打分高，预测为1，否则预测为 0。
 
 ```python
diff --git a/dssm/data/classification/test.txt b/dssm/data/classification/test.txt
index c8110d4e..66b81957 100644
--- a/dssm/data/classification/test.txt
+++ b/dssm/data/classification/test.txt
@@ -1,2 +1,2 @@
-新手 汽车 驾驶	驾校 培训	1
-苹果 六 袋	苹果 6s	0
+苹果	苹果 6s	0
+汽车 驾驶	驾校 培训	1
diff --git a/dssm/data/classification/train.txt b/dssm/data/classification/train.txt
index c8110d4e..05ab78a6 100644
--- a/dssm/data/classification/train.txt
+++ b/dssm/data/classification/train.txt
@@ -1,2 +1,2 @@
-新手 汽车 驾驶	驾校 培训	1
 苹果 六 袋	苹果 6s	0
+新手 汽车 驾驶	驾校 培训	1
diff --git a/dssm/data/rank/test.txt b/dssm/data/rank/test.txt
index f3dab7ce..093e2c36 100644
--- a/dssm/data/rank/test.txt
+++ b/dssm/data/rank/test.txt
@@ -1,2 +1,2 @@
-新手 汽车 驾驶	驾校 培训	苹果 6s	1
 苹果 六 袋	苹果 6s	新手 汽车 驾驶	1
+新手 汽车 驾驶	驾校 培训	苹果 6s	0
diff --git a/dssm/data/rank/train.txt b/dssm/data/rank/train.txt
index f3dab7ce..6557cfd0 100644
--- a/dssm/data/rank/train.txt
+++ b/dssm/data/rank/train.txt
@@ -1,2 +1,2 @@
-新手 汽车 驾驶	驾校 培训	苹果 6s	1
 苹果 六 袋	苹果 6s	新手 汽车 驾驶	1
+新手 汽车 驾驶	驾校 培训	苹果 6s	1
-- 
GitLab