From 5ea3c4352ee425c4db9fc09c7cbaedb65295a181 Mon Sep 17 00:00:00 2001
From: Luo Tao <luotao02@baidu.com>
Date: Mon, 6 Mar 2017 14:13:27 +0800
Subject: [PATCH] refine mnist demo

---
 label_semantic_roles/index.en.html | 599 ++++++++++++++---------------
 recognize_digits/README.en.md      |  99 +++--
 recognize_digits/README.md         | 103 +++--
 recognize_digits/index.en.html     | 315 +++++----------
 recognize_digits/index.html        | 126 +++---
 recognize_digits/train.py          | 111 ++++++
 recommender_system/index.en.html   |   2 +-
 word2vec/index.en.html             |   2 +-
 word2vec/index.html                | 307 +++++++--------
 9 files changed, 776 insertions(+), 888 deletions(-)
 create mode 100644 recognize_digits/train.py

diff --git a/label_semantic_roles/index.en.html b/label_semantic_roles/index.en.html
index 790fdb3..b29478e 100644
--- a/label_semantic_roles/index.en.html
+++ b/label_semantic_roles/index.en.html
@@ -41,24 +41,24 @@
 <div id="markdown" style='display:none'>
 # Semantic Role Labeling
 
-Source code of this chpater is in [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles).
+Source code of this chapter is in [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles).
 
 ## Background
 
-Natural Language Analysis contains three components: Lexical Analysis, Syntactic Analysis, and Semantic Analysis. Semantic Role Labelling (SRL) is one way for Shallow Semantic Analysis. A predicate of a sentence is seen as a property that a subject has or is characterized by, such as what it does, what it is or how it is, which mostly corresponds to the core of an event. The noun associated with predicate is called Arugment. Sementic roles express the abstract roles that arguments of a predicate can take in the event, such as Agent, Patient, Theme, Experiencer, Beneficiary, Instrument, Location, Goal and Source etc.
+Natural Language Analysis contains three components: Lexical Analysis, Syntactic Analysis, and Semantic Analysis. Semantic Role Labelling (SRL) is one way for Shallow Semantic Analysis. A predicate of a sentence is a property that a subject possesses or is characterized, such as what it does, what it is or how it is, which mostly corresponds to the core of an event. The noun associated with a predicate is called Argument. Semantic roles express the abstract roles that arguments of a predicate can take in the event, such as Agent, Patient, Theme, Experiencer, Beneficiary, Instrument, Location, Goal and Source, etc.
 
-In the following example, “遇到” is Predicate (“Pred”)，“小明” is Agent，“小红” is Patient，“昨天” means when the event occurs (Time), and “公园” means where the event occurs (Location).
+In the following example, “遇到” (encounters) is a Predicate (“Pred”)，“小明” (Ming) is an Agent，“小红” (Hong) is a Patient，“昨天” (yesterday) indicates the Time, and “公园” (park) is the Location.
 
 $$\mbox{[小明]}_{\mbox{Agent}}\mbox{[昨天]}_{\mbox{Time}}\mbox{[晚上]}_\mbox{Time}\mbox{在[公园]}_{\mbox{Location}}\mbox{[遇到]}_{\mbox{Predicate}}\mbox{了[小红]}_{\mbox{Patient}}\mbox{。}$$
 
-Instead of in-depth analysis on semantic information, the goal of Semantic Role Labeling is to identify the relation of predicate and other constituents, e.g., predicate-argument structure, as specific semantic roles, which is an important intermediate step in a wide range of natural language understanding tasks (Information Extraction, Discourse Analysis, DeepQA etc). Predicates are always assumed to be given, the only thing is to identify arguments and their semantic roles.
+Instead of in-depth analysis on semantic information, the goal of Semantic Role Labeling is to identify the relation of predicate and other constituents, e.g., predicate-argument structure, as specific semantic roles, which is an important intermediate step in a wide range of natural language understanding tasks (Information Extraction, Discourse Analysis, DeepQA etc). Predicates are always assumed to be given; the only thing is to identify arguments and their semantic roles.
 
-Standard SRL system mostly build on top of Syntactic Analysis and contains 5 steps:
+Standard SRL system mostly builds on top of Syntactic Analysis and contains five steps:
 
 1. Construct a syntactic parse tree, as shown in Fig. 1
 2. Identity candidate arguments of given predicate from constructed syntactic parse tree.
 3. Prune most unlikely candidate arguments.
-4. Identify argument, which is usually solved as a binary classification problem.
+4. Identify arguments, often by a binary classifier.
 5. Multi-class semantic role labeling. Steps 2-3 usually introduce hand-designed features based on Syntactic Analysis (step 1).
 
 
@@ -77,7 +77,7 @@ Fig 1. Syntactic parse tree
 标点-> WP
 
 
-However, complete syntactic analysis requires to identify the relation among all constitutes and the performance of SRL is sensitive to the precision of syntactic analysis, which make SRL a very challenging task. In order to reduce the complexity and obtain some syntactic structure information, shallow syntactic analysis is proposed. Shallow Syntactic Analysis is also called partial parsing or chunking. Unlike complete syntactic analysis which requires constructing complete parsing tree, Shallow Syntactic Analysis only need to identify some idependent components with relatively simple structure, such as verb phrases (chunk). In order to avoid constructing syntactic tree with high accuracy, some work\[[1](#Reference)\] proposed semantic chunking based SRL methods, which convert SRL as a sequence tagging problem.  Sequence tagging tasks classify syntactic chunks using BIO representation. For syntactic chunks forming a chunk of type A, the first chunk receives the B-A tag (Begin), the remaining ones receive the tag I-A (Inside), and all chunks outside receive the tag O-A.
+However, complete syntactic analysis requires identifying the relation among all constitutes and the performance of SRL is sensitive to the precision of syntactic analysis, which makes SRL a very challenging task. To reduce the complexity and obtain some syntactic structure information, we often use shallow syntactic analysis. Shallow Syntactic Analysis is also called partial parsing or chunking. Unlike complete syntactic analysis which requires the construction of the complete parsing tree, Shallow Syntactic Analysis only need to identify some independent components with relatively simple structure, such as verb phrases (chunk). To avoid difficulties in constructing a syntactic tree with high accuracy, some work\[[1](#Reference)\] proposed semantic chunking based SRL methods, which convert SRL as a sequence tagging problem. Sequence tagging tasks classify syntactic chunks using BIO representation. For syntactic chunks forming a chunk of type A, the first chunk receives the B-A tag (Begin), the remaining ones receive the tag I-A (Inside), and all chunks outside receive the tag O-A.
 
 The BIO representation of above example is shown in Fig.1.
 
@@ -91,23 +91,23 @@ Fig 2. BIO represention
 标注序列-> label sequence
 角色-> role
 
-This example illustrates the simplicity of sequence tagging because (1) shallow syntactic analysis reduces precision requirement of syntactic analysis; (2) pruning candidate arguments is removed; 3) argument identification and tagging are finished at the same time. Such unified methods simplify the precedure, reduce the risk of accumulating errors and boost the performance further.
+This example illustrates the simplicity of sequence tagging because (1) shallow syntactic analysis reduces the precision requirement of syntactic analysis; (2) pruning candidate arguments is removed; 3) argument identification and tagging are finished at the same time. Such unified methods simplify the procedure, reduce the risk of accumulating errors and boost the performance further.
 
-In this tutorial, our SRL system is built as an end-to-end system via neural network. We take only text sequences, without using any syntactic parsing results or complex hand-designed features. We give public dataset [CoNLL-2004 and CoNLL-2005 Shared Tasks](http://www.cs.upc.edu/~srlconll/) as an example to illustrate: given a sentence and it's predicates, identify the corresponding arguments and their semantic roles by sequence tagging method.
+In this tutorial, our SRL system is built as an end-to-end system via a neural network. We take only text sequences, without using any syntactic parsing results or complex hand-designed features. We give public dataset [CoNLL-2004 and CoNLL-2005 Shared Tasks](http://www.cs.upc.edu/~srlconll/) as an example to illustrate: given a sentence with predicates marked, identify the corresponding arguments and their semantic roles by sequence tagging method.
 
 ## Model
 
-Recurrent Nerual Networks are important tools for sequence modeling and have been successfully used in some natural language processing tasks. Unlike Feed-forward neural netowrks, RNNs can model the dependency between elements of sequences. LSTMs as variants of RNNs aim to model long-term dependency in long sequences. We have introduced this in [understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment). In this chapter, we continue to use LSTMs to solve SRL problems.
+Recurrent Neural Networks are important tools for sequence modeling and have been successfully used in some natural language processing tasks. Unlike Feed-forward neural networks, RNNs can model the dependency between elements of sequences. LSTMs as variants of RNNs aim to model long-term dependency in long sequences. We have introduced this in [understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment). In this chapter, we continue to use LSTMs to solve SRL problems.
 
 ### Stacked Recurrent Neural Network
 
-Deep Neural Networks allows to extract hierarchical represetations, higher layer can form more abstract/complex representations on top of lower layers. LSTMs when unfolded in time is deep, because a computational path between the input at time $k < t$ to the output at time $t$ crosses several nonlinear layers. However, the computation carried out at each time-step is only linear transformation, which makes LSTMs a shallow model. Deep LSTMs are typically constructed by stacking multiple LSTM layers on top of each other and taking the output from lower LSTM layer at time $t$ as the input of upper LSTM layer at time $t$. Deep, hierarchical nerual networks can be much efficient at representing some functions and modeling varying-length dependencies\[[2](#Reference)\].
+Deep Neural Networks allows extracting hierarchical representations. Higher layers can form more abstract/complex representations on top of lower layers. LSTMs, when unfolded in time, is a deep feed-forward neural network, because a computational path between the input at time $k < t$ to the output at time $t$ crosses several nonlinear layers. However, the computation carried out at each time-step is only linear transformation, which makes LSTMs a shallow model. Deep LSTMs are typically constructed by stacking multiple LSTM layers on top of each other and taking the output from lower LSTM layer at time $t$ as the input of upper LSTM layer at time $t$. Deep, hierarchical neural networks can be much efficient at representing some functions and modeling varying-length dependencies\[[2](#Reference)\].
 
 
-However, deep LSTMs increases the number of nonlinear steps the gradient has to traverse when propagated back in depth. For example, 4 layer LSTMs can be trained properly, but the performance becomes worse as the number of layers up to 4-8. Conventional LSTMs prevent backpropagated errors from vanishing and exploding by introduce shortcut connections to skip the intermediate nonlinear layers. Therefore, deep LSTMs can consider shortcut connections in depth as well.
+However, deep LSTMs increases the number of nonlinear steps the gradient has to traverse when propagated back in depth. For example, four layer LSTMs can be trained properly, but the performance becomes worse as the number of layers up to 4-8. Conventional LSTMs prevent backpropagated errors from vanishing and exploding by introducing shortcut connections to skip the intermediate nonlinear layers. Therefore, deep LSTMs can consider shortcut connections in depth as well.
 
 
-The operation of a single LSTM cell contain 3 parts: (1) input-to-hidden: map input $x$ to the input of forget gates, input gates, memory cells and output gates by linear transformation (i.e., matrix mapping); (2) hidden-to-hidden: calculate forget gates, input gates, output gates and update memory cell, this is the main part of LSTMs; (3)hidden-to-output: this part typically involves an activation operation on hidden states. Based on the above stacked LSTMs, we add a shortcut connection: take the input-to-hidden from previous layer as a new input and learn another linear transfermation.
+The operation of a single LSTM cell contain 3 parts: (1) input-to-hidden: map input $x$ to the input of the forget gates, input gates, memory cells and output gates by linear transformation (i.e., matrix mapping); (2) hidden-to-hidden: calculate forget gates, input gates, output gates and update memory cell, this is the main part of LSTMs; (3)hidden-to-output: this part typically involves an activation operation on hidden states. Based on the stacked LSTMs, we add a shortcut connection: take the input-to-hidden from the previous layer as a new input and learn another linear transformation.
 
 Fig.3 illustrate the final stacked recurrent neural networks.
 
@@ -121,7 +121,7 @@ Fig 3. Stacked Recurrent Neural Networks
 
 ### Bidirectional Recurrent Neural Network
 
- LSTMs can summarize the history of previous inputs seen up to now, but can not see the future. In most of natural language processing tasks, the entire sentences are ready to use. Therefore, sequencal learning might be much effecient if the future can be encoded as well like histories.
+LSTMs can summarize the history of previous inputs seen up to now, but can not see the future. In most of NLP (natural language processing) tasks, the entire sentences are ready to use. Therefore, sequential learning might be much efficient if the future can be encoded as well like histories.
 
 To address the above drawbacks, we can design bidirectional recurrent neural networks by making a minor modification. Higher LSTM layers process the sequence in reversed direction with previous lower LSTM layers, i.e., Deep LSTMs operate from left-to-right, right-to-left, left-to-right,..., in depth. Therefore, LSTM layers at time-step $t$ can see both histories and the future since the second layer. Fig. 4 illustrates the bidirectional recurrent neural networks.
 
@@ -133,10 +133,10 @@ Fig 4. Bidirectional LSTMs
 
 线性变换-> linear transformation
 输入层到隐层-> input-to-hidden
-正向处理输出序列->process sequence in forward direction
-反向处理上一层序列-> process sequence from previous layer in backward direction
+正向处理输出序列->process sequence in the forward direction
+反向处理上一层序列-> process sequence from the previous layer in backward direction
 
-Note that, this bidirectional RNNs is different with the one proposed by Bengio et al in machine translation tasks \[[3](#Reference), [4](#Reference)\]. We will introduce another bidirectional RNNs in the following tasks[machine translation](https://github.com/PaddlePaddle/book/blob/develop/machine_translation/README.md)
+Note that, this bidirectional RNNs is different with the one proposed by Bengio et al. in machine translation tasks \[[3](#Reference), [4](#Reference)\]. We will introduce another bidirectional RNNs in the following tasks[machine translation](https://github.com/PaddlePaddle/book/blob/develop/machine_translation/README.md)
 
 ### Conditional Random Field
 
@@ -145,7 +145,7 @@ The basic pipeline of Neural Networks solving problems is 1) all lower layers ai
 
 CRF is a probabilistic graph model (undirected) with nodes denoting random variables and edges denoting dependencies between nodes. To be simplicity, CRFs learn conditional probability $P(Y|X)$, where $X = (x_1, x_2, ... , x_n)$ are sequences of input, $Y = (y_1, y_2, ... , y_n)$ are label sequences; Decoding is to search sequence $Y$ to maximize conditional probability $P(Y|X)$, i.e., $Y^* = \mbox{arg max}_{Y} P(Y | X)$。
 
-Sequence tagging tasks only consider input and output as linear sequences without extra dependent assumptions on graph model. Thus, the graph model of sequence tagging tasks is simple chain or line, which results in a Linear Chain Conditional Random Field, shown in Fig.5.
+Sequence tagging tasks only consider input and output as linear sequences without extra dependent assumptions on graph model. Thus, the graph model of sequence tagging tasks is simple chain or line, which results in a Linear-Chain Conditional Random Field, shown in Fig.5.
 
 <p align="center">    
 <img src="./image/linear_chain_crf.png" width = "35%" align=center><br>
@@ -174,25 +174,25 @@ This objective function can be solved via back-propagation in an end-to-end mann
 Given predicates and a sentence, SRL tasks aim to identify arguments of the given predicate and their semantic roles. If a sequence has n predicates, we will process this sequence n times. One model is as follows:
 
 1. Construct inputs;
- - output 1: predicate, output 2: sentence
+ - input 1: predicate, input 2: sentence
  - expand input 1 as a sequence with the same length with input 2 using one-hot representation;
-2. Convert one-hot sequences from step 1 to real-vector sequences via lookup table;
-3. Learn the representation of input sequences by taking real-vector sequences from step 2 as inputs;
+2. Convert one-hot sequences from step 1 to vector sequences via lookup table;
+3. Learn the representation of input sequences by taking vector sequences from step 2 as inputs;
 4. Take representations from step 3 as inputs, label sequence as supervision signal, do sequence tagging tasks
 
 We can try above method. Here, we propose some modifications by introducing two simple but effective features:
 
 - predicate context (ctx-p): A single predicate word can not exactly describe the predicate information, especially when the same words appear more than one times in a sentence. With the expanded context, the ambiguity can be largely eliminated. Thus, we extract $n$ words before and after predicate to construct a window chunk.
 
-- region mark ($m_r$): $m_r = 1$ to denote the argument position if it locates in the predicate context region, or $m_r = 0$ if not.
+- region mark ($m_r$): $m_r = 1$ to denote word in that position locates in the predicate context region, or $m_r = 0$ if not.
 
 After modification, the model is as follows:
 
 1. Construct inputs
- - input 1: sentence, input 2: predicate sequence, input 3: predicate context, extract $n$ words before and after predicate and get one-hot representation, input 4: region mark, annotate argument position if it locates in the predicate context region
+ - Input 1: word sequence. Input 2: predicate. Input 3: predicate context, extract $n$ words before and after predicate. Input 4: region mark sequence, element value will be 1 if word locates in the predicate context region, 0 otherwise.
  - expand input 2~3 as sequences with the same length with input 1
-2. Convert input 1~4 to real-vector sequences via lookup table; input 1 and 3 share the same lookup table, input 2 and 4 have separate lookup tables
-3. Take four real-vector sequences from step 2 as inputs of bidirectional LSTMs; Train LSTMs to update representations
+2. Convert input 1~4 to vector sequences via lookup table; input 1 and 3 shares the same lookup table, input 2 and 4 have separate lookup tables
+3. Take four vector sequences from step 2 as inputs of bidirectional LSTMs; Train LSTMs to update representations
 4. Take representation from step 3 as input of CRF, label sequence as supervision signal, do sequence tagging tasks
 
 
@@ -209,12 +209,11 @@ Fig 6. DB-LSTM for SRL tasks
 原句-> sentence
 反向LSTM-> LSTM Reverse
 
-## 数据准备
-### 数据介绍与下载
+## Data Preparation
 
-在此教程中，我们选用[CoNLL 2005](http://www.cs.upc.edu/~srlconll/)SRL任务开放出的数据集作为示例。运行 `sh ./get_data.sh` 会自动从官方网站上下载原始数据。需要特别说明的是，CoNLL 2005 SRL任务的训练数集和开发集在比赛之后并非免费进行公开，目前，能够获取到的只有测试集，包括Wall Street Journal的23节和Brown语料集中的3节。在本教程中，我们以测试集中的WSJ数据为训练集来讲解模型。但是，由于测试集中样本的数量远远不够，如果希望训练一个可用的神经网络SRL系统，请考虑付费获取全量数据。
+In the tutorial, we use [CoNLL 2005](http://www.cs.upc.edu/~srlconll/) SRL task open dataset as an example. It is important to note that the training set and development set of the CoNLL 2005 SRL task are not free to download after the competition. Currently, only the test set can be obtained, including 23 sections of the Wall Street Journal and three sections of the Brown corpus. In this tutorial, we use the WSJ corpus as the training dataset to explain the model. However, since the training set is small, if you want to train a usable neural network SRL system, consider paying for the full corpus.
 
-原始数据中同时包括了词性标注、命名实体识别、语法解析树等多种信息。本教程中，我们使用test.wsj文件夹中的数据进行训练和测试，并只会用到words文件夹（文本序列）和props文件夹（标注结果）下的数据。本教程使用的数据目录如下：
+The original data includes a variety of information such as POS tagging, naming entity recognition, parsing tree, and so on. In this tutorial, we only use the data under the words folder (text sequence) and the props folder (label results) inside test.wsj parent folder. The data directory used in this tutorial is as follows:
 
 ```text
 conll05st-release/
@@ -223,30 +222,26 @@ conll05st-release/
     └── words  # 输入文本序列
 ```
 
-标注信息源自Penn TreeBank\[[7](#参考文献)\]和PropBank\[[8](#参考文献)\]的标注结果。PropBank标注结果的标签和我们在文章一开始示例中使用的标注结果标签不同，但原理是相同的，关于标注结果标签含义的说明，请参考论文\[[9](#参考文献)\]。
+The annotation information is derived from the results of Penn TreeBank\[[7](#references)\] and PropBank \[[8](# references)\]. The label of the PropBank is different from the label that we used in the example at the beginning of the article, but the principle is the same. For the description of the label, please refer to the paper \[[9](#references)\].
 
-除数据之外，`get_data.sh`同时下载了以下资源：
+The raw data needs to be preprocessed before used by PaddlePaddle. The preprocessing consists of the following steps:
 
-| 文件名称 | 说明 |
-|---|---|
-| word_dict | 输入句子的词典，共计44068个词 |
-| label_dict | 标记的词典，共计106个标记 |
-| predicate_dict | 谓词的词典，共计3162个词 |
-| emb | 一个训练好的词表，32维 |
-
-我们在英文维基百科上训练语言模型得到了一份词向量用来初始化SRL模型。在SRL模型训练过程中，词向量不再被更新。关于语言模型和词向量可以参考[词向量](https://github.com/PaddlePaddle/book/blob/develop/word2vec/README.md) 这篇教程。我们训练语言模型的语料共有995,000,000个token，词典大小控制为4900,000词。CoNLL 2005训练语料中有5%的词不在这4900,000个词中，我们将它们全部看作未登录词，用`<unk>`表示。
-
-### 数据预处理
-脚本在下载数据之后，又调用了`extract_pair.py`和`extract_dict_feature.py`两个子脚本进行数据预处理，前者完成了下面的第1步，后者完成了下面的2~4步：
+1. Merge the text sequence and the tag sequence into the same record;
+2. If a sentence contains $n$ predicates, the sentence will be processed $n$ times into $n$ separate training samples, each sample with a different predicate;
+3. Extract the predicate context and construct the predicate context region marker;
+4. Construct the markings in BIO format;
+5. Obtain the integer index corresponding to the word according to the dictionary.
 
-1. 将文本序列和标记序列其合并到一条记录中；
-2. 一个句子如果含有$n$个谓词，这个句子会被处理$n$次，变成$n$条独立的训练样本，每个样本一个不同的谓词；
-3. 抽取谓词上下文和构造谓词上下文区域标记；
-4. 构造以BIO法表示的标记；
+```python
+# import paddle.v2.dataset.conll05 as conll05
+# conll05.corpus_reader does step 1 and 2 as mentioned above.
+# conll05.reader_creator does step 3 to 5.
+# conll05.test gets preprocessed training instances.
+```
 
-`data/feature`文件是处理好的模型输入，一行是一条训练样本，以"\t"分隔，共9列，分别是：句子序列、谓词、谓词上下文（占 5 列）、谓词上下区域标志、标注序列。下表是一条训练样本的示例。
+After preprocessing completes, a training sample contains nine features, namely: word sequence, predicate, predicate context (5 columns), region mark sequence, label sequence. Following table is an example of a training sample.
 
-| 句子序列 | 谓词 | 谓词上下文（窗口 = 5） | 谓词上下文区域标记 | 标注序列 | 
+| word sequence | predicate | predicate context（5 columns） | region mark sequence | label sequence|
 |---|---|---|---|---|
 | A | set | n't been set . × | 0 | B-A1 |
 | record | set | n't been set . × | 0 | I-A1 |
@@ -257,293 +252,279 @@ conll05st-release/
 | set | set | n't been set . × | 1 | B-V |
 | . | set | n't been set . × | 1 | O |
 
-### 提供数据给 PaddlePaddle
-1. 使用hook函数进行PaddlePaddle输入字段的格式定义。
-
-	```python
-	def hook(settings, word_dict, label_dict, predicate_dict, **kwargs):
-	    settings.word_dict = word_dict   # 获取句子序列的字典
-	    settings.label_dict = label_dict  # 获取标记序列的字典
-	    settings.predicate_dict = predicate_dict  # 获取谓词的字典
-	
-	    #  所有输入特征都是使用one-hot表示序列，在PaddlePaddle中是interger_value_sequence类型
-	    #  input_types是一个字典，字典中每个元素对应着配置中的一个data_layer，key恰好就是data_layer的名字
-	    
-	    settings.input_types = {
-		        'word_data': integer_value_sequence(len(word_dict)),    # 句子序列
-		        'ctx_n2_data': integer_value_sequence(len(word_dict)),  # 谓词上下文中的第1个词
-		        'ctx_n1_data': integer_value_sequence(len(word_dict)),  # 谓词上下文中的第2个词
-		        'ctx_0_data': integer_value_sequence(len(word_dict)),   # 谓词上下文中的第3个词
-		        'ctx_p1_data': integer_value_sequence(len(word_dict)),  # 谓词上下文中的第4个词
-		        'ctx_p2_data': integer_value_sequence(len(word_dict)),  # 谓词上下文中的第5个词
-		        'verb_data': integer_value_sequence(len(predicate_dict)),  # 谓词
-		        'mark_data': integer_value_sequence(2),  # 谓词上下文区域标记
-		        'target': integer_value_sequence(len(label_dict))  # 标记序列
-        }
-	```
-
-2. 使用process将数据逐一提供给PaddlePaddle，只需要考虑如何从原始数据文件中返回一条训练样本。
-
-	```python
-	def process(settings, file_name):
-	    with open(file_name, 'r') as fdata:
-	        for line in fdata:
-	            sentence, predicate, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2,  mark, label = \
-	                line.strip().split('\t')
-	
-	            # 句子文本
-	            words = sentence.split()
-	            sen_len = len(words)
-	            word_slot = [settings.word_dict.get(w, UNK_IDX) for w in words]
-	
-	            # 一个谓词，这里将谓词扩展成一个和句子一样长的序列
-	            predicate_slot = [settings.predicate_dict.get(predicate)] * sen_len
-	            
-	            # 在教程中，我们使用一个窗口为 5 的谓词上下文窗口：谓词和这个谓词前后隔两个词
-	            # 这里会将窗口中的每一个词，扩展成和输入句子一样长的序列
-	            ctx_n2_slot = [settings.word_dict.get(ctx_n2, UNK_IDX)] * sen_len
-	            ctx_n1_slot = [settings.word_dict.get(ctx_n1, UNK_IDX)] * sen_len
-	            ctx_0_slot = [settings.word_dict.get(ctx_0, UNK_IDX)] * sen_len
-	            ctx_p1_slot = [settings.word_dict.get(ctx_p1, UNK_IDX)] * sen_len
-	            ctx_p2_slot = [settings.word_dict.get(ctx_p2, UNK_IDX)] * sen_len
-	
-	            # 谓词上下文区域标记，是一个二值特征
-	            marks = mark.split()
-	            mark_slot = [int(w) for w in marks]
-	
-	            label_list = label.split()
-	            label_slot = [settings.label_dict.get(w) for w in label_list]
-	            yield {
-	                'word_data': word_slot,
-	                'ctx_n2_data': ctx_n2_slot,
-	                'ctx_n1_data': ctx_n1_slot,
-	                'ctx_0_data': ctx_0_slot,
-	                'ctx_p1_data': ctx_p1_slot,
-	                'ctx_p2_data': ctx_p2_slot,
-	                'verb_data': predicate_slot,
-	                'mark_data': mark_slot,
-	                'target': label_slot
-	            }	
-	```
-
-## 模型配置说明
-
-### 数据定义
-
-首先通过 define_py_data_sources2 从dataprovider中读入数据。配置文件中会读取三个字典：输入文本序列的字典、标记的字典、谓词的字典，并传给data provider，data provider会利用这三个字典，将相应的文本输入转换成one-hot序列。
+In addition to the data, we provide following resources:
+
+| filename | explanation |
+|---|---|
+| word_dict | dictionary of input sentences, total 44068 words |
+| label_dict | dictionary of labels, total 106 labels |
+| predicate_dict | predicate dictionary, total 3162 predicates |
+| emb | a pre-trained word vector lookup table, 32-dimentional |
+
+We trained in the English Wikipedia language model to get a word vector lookup table used to initialize the SRL model. During the SRL model training process, the word vector lookup table is no longer updated. About the language model and the word vector lookup table can refer to [word vector](https://github.com/PaddlePaddle/book/blob/develop/word2vec/README.md) tutorial. There are 995,000,000 token in training corpus, and the dictionary size is 4900,000 words. In the CoNLL 2005 training corpus, 5% of the words are not in the 4900,000 words, and we see them all as unknown words, represented by `<unk>`.
+
+Get dictionary, print dictionary size:
 
 ```python
-define_py_data_sources2(
-        train_list=train_list_file,
-        test_list=test_list_file,
-        module='dataprovider',
-        obj='process',
-        args={
-            'word_dict': word_dict,   # 输入文本序列的字典
-            'label_dict': label_dict, # 标记的字典
-            'predicate_dict': predicate_dict  # 谓词的词典
-        }
-)
+import paddle.v2 as paddle
+import paddle.v2.dataset.conll05 as conll05
+
+word_dict, verb_dict, label_dict = conll05.get_dict()
+word_dict_len = len(word_dict)
+label_dict_len = len(label_dict)
+pred_len = len(verb_dict)
+
+print len(word_dict_len)
+print len(label_dict_len)
+print len(pred_len)
 ```
-### 算法配置
 
-在这里，我们指定了模型的训练参数，选择了$L_2$正则、学习率和batch size，并使用带Momentum的随机梯度下降法作为优化算法。
+## Model configuration
+
+1. Define input data dimensions and model hyperparameters.
+
+    ```python
+    mark_dict_len = 2    # Value range of region mark. Region mark is either 0 or 1, so range is 2
+    word_dim = 32        # word vector dimension
+    mark_dim = 5         # adjacent dimension
+    hidden_dim = 512     # the dimension of LSTM hidden layer vector is 128 (512/4)
+    depth = 8            # depth of stacked LSTM
+    
+    # There are 9 features per sample, so we will define 9 data layers.
+    # They type for each layer is integer_value_sequence.
+    def d_type(value_range):
+        return paddle.data_type.integer_value_sequence(value_range)
+
+    # word sequence
+    word = paddle.layer.data(name='word_data', type=d_type(word_dict_len))
+    # predicate
+    predicate = paddle.layer.data(name='verb_data', type=d_type(pred_len)) 
+
+    # 5 features for predicate context
+    ctx_n2 = paddle.layer.data(name='ctx_n2_data', type=d_type(word_dict_len)) 
+    ctx_n1 = paddle.layer.data(name='ctx_n1_data', type=d_type(word_dict_len))
+    ctx_0 = paddle.layer.data(name='ctx_0_data', type=d_type(word_dict_len))
+    ctx_p1 = paddle.layer.data(name='ctx_p1_data', type=d_type(word_dict_len))
+    ctx_p2 = paddle.layer.data(name='ctx_p2_data', type=d_type(word_dict_len))
+    
+    # region marker sequence
+    mark = paddle.layer.data(name='mark_data', type=d_type(mark_dict_len))
+    
+    # label sequence
+    target = paddle.layer.data(name='target', type=d_type(label_dict_len))
+    ```
+    
+   Speciala note: hidden_dim = 512 means LSTM hidden vector of 128 dimension (512/4). Please refer PaddlePaddle official documentation for detail: [lstmemory](http://www.paddlepaddle.org/doc/ui/api/trainer_config_helpers/layers.html#lstmemory)。
+
+2. The word sequence, predicate, predicate context, and region mark sequence are transformed into embedding vector sequences.
+
+    ```python   
+   
+    # Since word vectorlookup table is pre-trained, we won't update it this time.
+    # is_static being True prevents updating the lookup table during training.
+    emb_para = paddle.attr.Param(name='emb', initial_std=0., is_static=True)
+    # hyperparameter configurations
+    default_std = 1 / math.sqrt(hidden_dim) / 3.0
+    std_default = paddle.attr.Param(initial_std=default_std)
+    std_0 = paddle.attr.Param(initial_std=0.)
+
+    predicate_embedding = paddle.layer.embedding(
+        size=word_dim,
+        input=predicate,
+        param_attr=paddle.attr.Param(
+            name='vemb', initial_std=default_std))
+    mark_embedding = paddle.layer.embedding(
+        size=mark_dim, input=mark, param_attr=std_0)
+
+    word_input = [word, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2]
+    emb_layers = [
+        paddle.layer.embedding(
+            size=word_dim, input=x, param_attr=emb_para) for x in word_input
+    ]
+    emb_layers.append(predicate_embedding)
+    emb_layers.append(mark_embedding)
+    ```
+
+3. 8 LSTM units will be trained in "forward / backward" order.
+
+    ```python  
+    hidden_0 = paddle.layer.mixed(
+        size=hidden_dim,
+        bias_attr=std_default,
+        input=[
+            paddle.layer.full_matrix_projection(
+                input=emb, param_attr=std_default) for emb in emb_layers
+        ])
+
+    mix_hidden_lr = 1e-3
+    lstm_para_attr = paddle.attr.Param(initial_std=0.0, learning_rate=1.0)
+    hidden_para_attr = paddle.attr.Param(
+        initial_std=default_std, learning_rate=mix_hidden_lr)
+
+    lstm_0 = paddle.layer.lstmemory(
+        input=hidden_0,
+        act=paddle.activation.Relu(),
+        gate_act=paddle.activation.Sigmoid(),
+        state_act=paddle.activation.Sigmoid(),
+        bias_attr=std_0,
+        param_attr=lstm_para_attr)
+
+    # stack L-LSTM and R-LSTM with direct edges
+    input_tmp = [hidden_0, lstm_0]
+
+    for i in range(1, depth):
+        mix_hidden = paddle.layer.mixed(
+            size=hidden_dim,
+            bias_attr=std_default,
+            input=[
+                paddle.layer.full_matrix_projection(
+                    input=input_tmp[0], param_attr=hidden_para_attr),
+                paddle.layer.full_matrix_projection(
+                    input=input_tmp[1], param_attr=lstm_para_attr)
+            ])
+
+        lstm = paddle.layer.lstmemory(
+            input=mix_hidden,
+            act=paddle.activation.Relu(),
+            gate_act=paddle.activation.Sigmoid(),
+            state_act=paddle.activation.Sigmoid(),
+            reverse=((i % 2) == 1),
+            bias_attr=std_0,
+            param_attr=lstm_para_attr)
+
+        input_tmp = [mix_hidden, lstm]
+    ```
+
+4. We will concatenate the output of top LSTM unit with it's input, and project into a hidden layer. Then put a fully connected layer on top of it to get the final vector representation.
+
+    ```python
+    feature_out = paddle.layer.mixed(
+    size=label_dict_len,
+    bias_attr=std_default,
+    input=[
+        paddle.layer.full_matrix_projection(
+            input=input_tmp[0], param_attr=hidden_para_attr),
+        paddle.layer.full_matrix_projection(
+            input=input_tmp[1], param_attr=lstm_para_attr)
+    ], )
+    ```
+
+5.  We use CRF as cost function, the parameter of CRF cost will be named `crfw`.
+
+    ```python
+    crf_cost = paddle.layer.crf(
+        size=label_dict_len,
+        input=feature_out,
+        label=target,
+        param_attr=paddle.attr.Param(
+            name='crfw',
+            initial_std=default_std,
+            learning_rate=mix_hidden_lr))
+    ```
+
+6.  CRF decoding layer is used for evaluation and inference. It shares parameter with CRF layer.  The sharing of parameters among multiple layers is specified by the same parameter name in these layers.
+
+    ```python
+    crf_dec = paddle.layer.crf_decoding(
+       name='crf_dec_l',
+       size=label_dict_len,
+       input=feature_out,
+       label=target,
+       param_attr=paddle.attr.Param(name='crfw'))
+    ```
+
+## Train model
+
+### Create Parameters
+
+All necessary parameters will be traced created given output layers that we need to use.
 
 ```python
-settings(
-    batch_size=150,
-    learning_method=MomentumOptimizer(momentum=0),
-    learning_rate=2e-2,
-    regularization=L2Regularization(8e-4),
-    model_average=ModelAverage(average_window=0.5, max_average_window=10000)
-)
+parameters = paddle.parameters.create([crf_cost, crf_dec])
 ```
 
-### 模型结构
-
-1. 定义输入数据维度及模型超参数。
-
-	```python
-	mark_dict_len = 2    # 谓上下文区域标志的维度，是一个0-1 2值特征，因此维度为2
-	word_dim = 32        # 词向量维度
-	mark_dim = 5         # 谓词上下文区域通过词表被映射为一个实向量，这个是相邻的维度
-	hidden_dim = 512     # LSTM隐层向量的维度 ： 512 / 4
-	depth = 8            # 栈式LSTM的深度
-	
-	word = data_layer(name='word_data', size=word_dict_len)
-   predicate = data_layer(name='verb_data', size=pred_len)
-
-	ctx_n2 = data_layer(name='ctx_n2_data', size=word_dict_len)
-	ctx_n1 = data_layer(name='ctx_n1_data', size=word_dict_len)
-	ctx_0 = data_layer(name='ctx_0_data', size=word_dict_len)
-	ctx_p1 = data_layer(name='ctx_p1_data', size=word_dict_len)
-	ctx_p2 = data_layer(name='ctx_p2_data', size=word_dict_len)
-	mark = data_layer(name='mark_data', size=mark_dict_len)
-	
-	if not is_predict:
-	    target = data_layer(name='target', size=label_dict_len)    # 标记序列只在训练和测试流程中定义
-	```
-这里需要特别说明的是hidden_dim = 512指定了LSTM隐层向量的维度为128维，关于这一点请参考PaddlePaddle官方文档中[lstmemory](http://www.paddlepaddle.org/doc/ui/api/trainer_config_helpers/layers.html#lstmemory)的说明。
-
-2. 将句子序列、谓词、谓词上下文、谓词上下文区域标记通过词表，转换为实向量表示的词向量序列。
-
-	```python
-	
-	# 在本教程中，我们加载了预训练的词向量，这里设置了：is_static=True
-	# is_static 为 True 时保证了在训练 SRL 模型过程中，词表不再更新
-	emb_para = ParameterAttribute(name='emb', initial_std=0., is_static=True)
-		
-	word_input = [word, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2]
-	emb_layers = [
-		    embedding_layer(
-		        size=word_dim, input=x, param_attr=emb_para) for x in word_input
-	]
-	emb_layers.append(predicate_embedding)
-	mark_embedding = embedding_layer(
-		    name='word_ctx-in_embedding', size=mark_dim, input=mark, param_attr=std_0)
-   emb_layers.append(mark_embedding)
-	```
-
-3. 8个LSTM单元以“正向/反向”的顺序对所有输入序列进行学习。
-
-	```python
-	#  std_0 指定的参数以均值为0的高斯分布初始化，用在LSTM的bias初始化中  
-	std_0 = ParameterAttribute(initial_std=0.)
-	
-	hidden_0 = mixed_layer(
-	    name='hidden0',
-	    size=hidden_dim,
-	    bias_attr=std_default,
-	    input=[
-	        full_matrix_projection(
-	            input=emb, param_attr=std_default) for emb in emb_layers
-	    ])
-	lstm_0 = lstmemory(
-	    name='lstm0',
-	    input=hidden_0,
-	    act=ReluActivation(),
-	    gate_act=SigmoidActivation(),
-	    state_act=SigmoidActivation(),
-	    bias_attr=std_0,
-	    param_attr=lstm_para_attr)
-		input_tmp = [hidden_0, lstm_0]
-
-	for i in range(1, depth):
-	    mix_hidden = mixed_layer(
-	        name='hidden' + str(i),
-	        size=hidden_dim,
-	        bias_attr=std_default,
-	        input=[
-	            full_matrix_projection(
-	                input=input_tmp[0], param_attr=hidden_para_attr),
-	            full_matrix_projection(
-	                input=input_tmp[1], param_attr=lstm_para_attr)
-	        ])
-	    lstm = lstmemory(
-	        name='lstm' + str(i),
-	        input=mix_hidden,
-	        act=ReluActivation(),
-	        gate_act=SigmoidActivation(),
-	        state_act=SigmoidActivation(),
-	        reverse=((i % 2) == 1),
-	        bias_attr=std_0,
-	        param_attr=lstm_para_attr)
-	
-	    input_tmp = [mix_hidden, lstm]
-	```
-
-4. 取最后一个栈式LSTM的输出和这个LSTM单元的输入到隐层映射，经过一个全连接层映射到标记字典的维度，得到最终的特征向量表示。
-
-	```python
-	feature_out = mixed_layer(
-	    name='output',
-	    size=label_dict_len,
-	    bias_attr=std_default,
-	    input=[
-	        full_matrix_projection(
-	            input=input_tmp[0], param_attr=hidden_para_attr),
-	        full_matrix_projection(
-	            input=input_tmp[1], param_attr=lstm_para_attr)
-	    ], ) 
-	```
-
-5.  CRF层在网络的末端，完成序列标注。
-
-	```python
-	crf_l = crf_layer(
-	        name='crf',
-	        size=label_dict_len,
-	        input=feature_out,
-	        label=target,
-	        param_attr=ParameterAttribute(
-	            name='crfw', initial_std=default_std, learning_rate=mix_hidden_lr))
-	```
-
-## 训练模型
-执行`sh train.sh`进行模型的训练，其中指定了总共需要训练150个pass。
-
-```bash
-paddle train \
-  --config=./db_lstm.py \
-  --save_dir=./output \
-  --trainer_count=1 \
-  --dot_period=500 \
-  --log_period=10 \
-  --num_passes=200 \
-  --use_gpu=false \
-  --show_parameter_stats_period=10 \
-  --test_all_data_in_one_period=1 \
-2>&1 | tee 'train.log'
+We can print out parameter name. It will be generated if not specified.
+   
+```python
+print parameters.keys()
 ```
 
-训练日志示例如下。
+Now we load pre-trained word lookup table.
 
-```text
-I1224 18:11:53.661479  1433 TrainerInternal.cpp:165]  Batch=880 samples=145305 AvgCost=2.11541 CurrentCost=1.8645 Eval: __sum_evaluator_0__=0.607942  CurrentEval: __sum_evaluator_0__=0.59322
-I1224 18:11:55.254021  1433 TrainerInternal.cpp:165]  Batch=885 samples=146134 AvgCost=2.11408 CurrentCost=1.88156 Eval: __sum_evaluator_0__=0.607299  CurrentEval: __sum_evaluator_0__=0.494572
-I1224 18:11:56.867604  1433 TrainerInternal.cpp:165]  Batch=890 samples=146987 AvgCost=2.11277 CurrentCost=1.88839 Eval: __sum_evaluator_0__=0.607203  CurrentEval: __sum_evaluator_0__=0.590856
-I1224 18:11:58.424069  1433 TrainerInternal.cpp:165]  Batch=895 samples=147793 AvgCost=2.11129 CurrentCost=1.84247 Eval: __sum_evaluator_0__=0.607099  CurrentEval: __sum_evaluator_0__=0.588089
-I1224 18:12:00.006893  1433 TrainerInternal.cpp:165]  Batch=900 samples=148611 AvgCost=2.11148 CurrentCost=2.14526 Eval: __sum_evaluator_0__=0.607882  CurrentEval: __sum_evaluator_0__=0.749389
-I1224 18:12:00.164089  1433 TrainerInternal.cpp:181]  Pass=0 Batch=901 samples=148647 AvgCost=2.11195 Eval: __sum_evaluator_0__=0.60793
+```python
+def load_parameter(file_name, h, w):
+    with open(file_name, 'rb') as f:
+         f.read(16)
+         return np.fromfile(f, dtype=np.float32).reshape(h, w)
+parameters.set('emb', load_parameter(conll05.get_embedding(), 44068, 32))
 ```
-经过150个 pass 后，得到平均 error 约为 0.0516055。
 
-## 应用模型
+### Create Trainer
+
+We will create trainer given model topology, parameters and optimization method. We will use most basic SGD method (momentum optimizer with 0 momentum). In the meantime, we will set learning rate and regularization.
+
+```python
+optimizer = paddle.optimizer.Momentum(
+    momentum=0,
+    learning_rate=2e-2,
+    regularization=paddle.optimizer.L2Regularization(rate=8e-4),
+    model_average=paddle.optimizer.ModelAverage(
+        average_window=0.5, max_average_window=10000), )
+
+trainer = paddle.trainer.SGD(cost=crf_cost,
+                             parameters=parameters,
+                             update_equation=optimizer)
+```
 
-训练好的$N$个pass，会得到$N$个模型，我们需要从中选择一个最优模型进行预测。通常做法是在开发集上进行调参，并基于我们关心的某个性能指标选择最优模型。本教程的`predict.sh`脚本简单地选择了测试集上标记错误最少的那个pass（这里是pass-00100）用于预测。
+### Trainer
 
-预测时，我们需要将配置中的 `crf_layer` 删掉，替换为 `crf_decoding_layer`，如下所示：
+As mentioned in data preparation section, we will use CoNLL 2005 test corpus as training data set. `conll05.test()` outputs one training instance at a time. It will be shuffled, and batched into mini batches as input.
 
 ```python
-crf_dec_l = crf_decoding_layer(
-        name='crf_dec_l',
-        size=label_dict_len,
-        input=feature_out,
-        param_attr=ParameterAttribute(name='crfw'))
+reader = paddle.reader.batched(
+    paddle.reader.shuffle(
+        conll05.test(), buf_size=8192), batch_size=20)
 ```
 
-运行`python predict.py`脚本，便可使用指定的模型进行预测。
-
-```bash
-python predict.py
-     -c db_lstm.py  # 指定配置文件
-     -w output/pass-00100  # 指定预测使用的模型所在的路径
-     -l data/targetDict.txt  # 指定标记的字典
-     -p data/verbDict.txt  # 指定谓词的词典
-     -d data/wordDict.txt # 指定输入文本序列的字典
-     -i data/feature  # 指定输入数据的路径
-     -o predict.res  # 指定标记结果输出到文件的路径
+`reader_dict` is used to specify relationship between data instance and layer layer. For example, according to following `reader_dict`, the 0th column of data instance produced by`conll05.test()` correspond to data layer named `word_data`.
+
+```python
+reader_dict = {
+    'word_data': 0,
+    'ctx_n2_data': 1,
+    'ctx_n1_data': 2,
+    'ctx_0_data': 3,
+    'ctx_p1_data': 4,
+    'ctx_p2_data': 5,
+    'verb_data': 6,
+    'mark_data': 7,
+    'target': 8
+}
 ```
 
-预测结束后，在 - o 参数所指定的标记结果文件中，我们会得到如下格式的输出：每行是一条样本，以 “\t” 分隔的 2 列，第一列是输入文本，第二列是标记的结果。通过BIO标记可以直接得到论元的语义角色标签。
+`event_handle` can be used as callback for training events, it will be used as an argument for `train`. Following `event_handle` prints cost during training.
 
-```text
-The interest-only securities were priced at 35 1\/2 to yield 10.72 % .  B-A0 I-A0 I-A0 O O O O O O B-V B-A1 I-A1 O
+```python
+def event_handler(event):
+    if isinstance(event, paddle.event.EndIteration):
+        if event.batch_id % 100 == 0:
+            print "Pass %d, Batch %d, Cost %f" % (
+                event.pass_id, event.batch_id, event.cost)
+```
+
+`trainer.train` will train the model.
+
+```python
+trainer.train(
+    reader=reader,
+    event_handler=event_handler,
+    num_passes=10000,
+    reader_dict=reader_dict)
 ```
 
 ## Conclusion
 
-Semantic Role Labeling is an important intermediate step in a wide range of natural language processing tasks. In this tutorial, we give SRL as an example to introduce how to use PaddlePaddle to do sequence tagging tasks. Proposed models are from our published paper\[[10](#Reference)\]. We only use test data as illustration since train data on CoNLL 2005 dataset is not completely public. We hope to propose an end-to-end neural network model with less dependencies on natural language processing tools, but is comparable, or even better than trandional models. Please check out our paper for more information and discussions.
+Semantic Role Labeling is an important intermediate step in a wide range of natural language processing tasks. In this tutorial, we give SRL as an example to introduce how to use PaddlePaddle to do sequence tagging tasks. Proposed models are from our published paper\[[10](#Reference)\]. We only use test data as an illustration since train data on CoNLL 2005 dataset is not completely public. We hope to propose an end-to-end neural network model with fewer dependencies on natural language processing tools but is comparable, or even better than traditional models. Please check out our paper for more information and discussions.
 
 ## Reference
 1. Sun W, Sui Z, Wang M, et al. [Chinese semantic role labeling with shallow parsing](http://www.aclweb.org/anthology/D09-1#page=1513)[C]//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3-Volume 3. Association for Computational Linguistics, 2009: 1475-1483.
diff --git a/recognize_digits/README.en.md b/recognize_digits/README.en.md
index 3192a10..3357963 100644
--- a/recognize_digits/README.en.md
+++ b/recognize_digits/README.en.md
@@ -196,34 +196,33 @@ def convolutional_neural_network(img):
 PaddlePaddle provides a special layer `layer.data` for reading data. Let us create a data layer for reading images and connect it to a classification network created using one of above three functions.  We also need a cost layer for training the model.
 
 ```python
-def main():
-    paddle.init(use_gpu=False, trainer_count=1)
+paddle.init(use_gpu=False, trainer_count=1)
 
-    images = paddle.layer.data(
-        name='pixel', type=paddle.data_type.dense_vector(784))
-    label = paddle.layer.data(
-        name='label', type=paddle.data_type.integer_value(10))
+images = paddle.layer.data(
+    name='pixel', type=paddle.data_type.dense_vector(784))
+label = paddle.layer.data(
+    name='label', type=paddle.data_type.integer_value(10))
 
-    predict = softmax_regression(images)
-    #predict = multilayer_perceptron(images) # uncomment for MLP
-    #predict = convolutional_neural_network(images) # uncomment for LeNet5
+predict = softmax_regression(images)
+#predict = multilayer_perceptron(images) # uncomment for MLP
+#predict = convolutional_neural_network(images) # uncomment for LeNet5
 
-    cost = paddle.layer.classification_cost(input=predict, label=label)
+cost = paddle.layer.classification_cost(input=predict, label=label)
 ```
 
 Now, it is time to specify training parameters. The number 0.9 in the following `Momentum` optimizer means that 90% of the current the momentum comes from the momentum of the previous iteration.
 
 ```python
-    parameters = paddle.parameters.create(cost)
+parameters = paddle.parameters.create(cost)
 
-    optimizer = paddle.optimizer.Momentum(
-        learning_rate=0.1 / 128.0,
-        momentum=0.9,
-        regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
+optimizer = paddle.optimizer.Momentum(
+    learning_rate=0.1 / 128.0,
+    momentum=0.9,
+    regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
 
-    trainer = paddle.trainer.SGD(cost=cost,
-                                 parameters=parameters,
-                                 update_equation=optimizer)
+trainer = paddle.trainer.SGD(cost=cost,
+                             parameters=parameters,
+                             update_equation=optimizer)
 ```
 
 Then we specify the training data `paddle.dataset.movielens.train()` and testing data `paddle.dataset.movielens.test()`.  These two functions are *reader creators*, once called, returns a *reader*.  A reader is a Python function, which, once called, returns a Python generator, which yields instances of data.  
@@ -233,48 +232,48 @@ Here `shuffle` is a reader decorator, which takes a reader A as its parameter, a
 `batch` is a special decorator, whose input is a reader and output is a *batch reader*, which doesn't yield an instance at a time, but a minibatch.
 
 ```python
-    lists = []
-
-    def event_handler(event):
-        if isinstance(event, paddle.event.EndIteration):
-            if event.batch_id % 100 == 0:
-                print "Pass %d, Batch %d, Cost %f, %s" % (
-                    event.pass_id, event.batch_id, event.cost, event.metrics)
-        if isinstance(event, paddle.event.EndPass):
-            result = trainer.test(reader=paddle.reader.batched(
-                paddle.dataset.mnist.test(), batch_size=128))
-            print "Test with Pass %d, Cost %f, %s\n" % (
-                event.pass_id, result.cost, result.metrics)
-            lists.append((event.pass_id, result.cost,
-                          result.metrics['classification_error_evaluator']))
-
-    trainer.train(
-        reader=paddle.reader.batched(
-            paddle.reader.shuffle(
-                paddle.dataset.mnist.train(), buf_size=8192),
-            batch_size=128),
-        event_handler=event_handler,
-        num_passes=100)
+lists = []
+
+def event_handler(event):
+    if isinstance(event, paddle.event.EndIteration):
+        if event.batch_id % 100 == 0:
+            print "Pass %d, Batch %d, Cost %f, %s" % (
+                event.pass_id, event.batch_id, event.cost, event.metrics)
+    if isinstance(event, paddle.event.EndPass):
+        result = trainer.test(reader=paddle.reader.batched(
+            paddle.dataset.mnist.test(), batch_size=128))
+        print "Test with Pass %d, Cost %f, %s\n" % (
+            event.pass_id, result.cost, result.metrics)
+        lists.append((event.pass_id, result.cost,
+                      result.metrics['classification_error_evaluator']))
+
+trainer.train(
+    reader=paddle.reader.batched(
+        paddle.reader.shuffle(
+            paddle.dataset.mnist.train(), buf_size=8192),
+        batch_size=128),
+    event_handler=event_handler,
+    num_passes=100)
 ```
 
 During training, `trainer.train` invokes `event_handler` for certain events. This gives us a chance to print the training progress.
 
 ```
-    # Pass 0, Batch 0, Cost 2.780790, {'classification_error_evaluator': 0.9453125}
-    # Pass 0, Batch 100, Cost 0.635356, {'classification_error_evaluator': 0.2109375}
-    # Pass 0, Batch 200, Cost 0.326094, {'classification_error_evaluator': 0.1328125}
-    # Pass 0, Batch 300, Cost 0.361920, {'classification_error_evaluator': 0.1015625}
-    # Pass 0, Batch 400, Cost 0.410101, {'classification_error_evaluator': 0.125}
-    # Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
+# Pass 0, Batch 0, Cost 2.780790, {'classification_error_evaluator': 0.9453125}
+# Pass 0, Batch 100, Cost 0.635356, {'classification_error_evaluator': 0.2109375}
+# Pass 0, Batch 200, Cost 0.326094, {'classification_error_evaluator': 0.1328125}
+# Pass 0, Batch 300, Cost 0.361920, {'classification_error_evaluator': 0.1015625}
+# Pass 0, Batch 400, Cost 0.410101, {'classification_error_evaluator': 0.125}
+# Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
 ```
 
 After the training, we can check the model's prediction accuracy.
 
 ```
-    # find the best pass
-    best = sorted(lists, key=lambda list: float(list[1]))[0]
-    print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
-    print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
+# find the best pass
+best = sorted(lists, key=lambda list: float(list[1]))[0]
+print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
+print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
 ```
 
 Usually, with MNIST data, the softmax regression model can get accuracy around 92.34%, MLP can get about 97.66%, and convolution network can get up to around 99.20%.  Convolution layers have been widely considered a great invention for image processsing.
diff --git a/recognize_digits/README.md b/recognize_digits/README.md
index 760de44..02e7db9 100644
--- a/recognize_digits/README.md
+++ b/recognize_digits/README.md
@@ -195,20 +195,19 @@ def convolutional_neural_network(img):
 接着，通过`layer.data`调用来获取数据，然后调用分类器（这里我们提供了三个不同的分类器）得到分类结果。训练时，对该结果计算其损失函数，分类问题常常选择交叉熵损失函数。
 
 ```python
-def main():
-    # 该模型运行在单个CPU上
-    paddle.init(use_gpu=False, trainer_count=1)
-
-    images = paddle.layer.data(
-        name='pixel', type=paddle.data_type.dense_vector(784))
-    label = paddle.layer.data(
-        name='label', type=paddle.data_type.integer_value(10))
-
-    predict = softmax_regression(images) # Softmax回归
-    #predict = multilayer_perceptron(images) #多层感知器
-    #predict = convolutional_neural_network(images) #LeNet5卷积神经网络
-
-    cost = paddle.layer.classification_cost(input=predict, label=label)
+# 该模型运行在单个CPU上
+paddle.init(use_gpu=False, trainer_count=1)
+
+images = paddle.layer.data(
+    name='pixel', type=paddle.data_type.dense_vector(784))
+label = paddle.layer.data(
+    name='label', type=paddle.data_type.integer_value(10))
+
+predict = softmax_regression(images) # Softmax回归
+#predict = multilayer_perceptron(images) #多层感知器
+#predict = convolutional_neural_network(images) #LeNet5卷积神经网络
+
+cost = paddle.layer.classification_cost(input=predict, label=label)
 ```
 
 然后，指定训练相关的参数。
@@ -217,16 +216,16 @@ def main():
 - 正则化（regularization）： 是防止网络过拟合的一种手段，此处采用L2正则化。
 
 ```python
-    parameters = paddle.parameters.create(cost)
-
-    optimizer = paddle.optimizer.Momentum(
-        learning_rate=0.1 / 128.0,
-        momentum=0.9,
-        regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
-
-    trainer = paddle.trainer.SGD(cost=cost,
-                                 parameters=parameters,
-                                 update_equation=optimizer)
+parameters = paddle.parameters.create(cost)
+
+optimizer = paddle.optimizer.Momentum(
+    learning_rate=0.1 / 128.0,
+    momentum=0.9,
+    regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
+
+trainer = paddle.trainer.SGD(cost=cost,
+                             parameters=parameters,
+                             update_equation=optimizer)
 ```
 
 下一步，我们开始训练过程。`paddle.dataset.movielens.train()`和`paddle.dataset.movielens.test()`分别做训练和测试数据集。这两个函数各自返回一个reader——PaddlePaddle中的reader是一个Python函数，每次调用的时候返回一个Python yield generator。
@@ -236,39 +235,39 @@ def main():
 `batch`是一个特殊的decorator，它的输入是一个reader，输出是一个batched reader —— 在PaddlePaddle里，一个reader每次yield一条训练数据，而一个batched reader每次yield一个minbatch。
 
 ```python
-    lists = []
-
-    def event_handler(event):
-        if isinstance(event, paddle.event.EndIteration):
-            if event.batch_id % 100 == 0:
-                print "Pass %d, Batch %d, Cost %f, %s" % (
-                    event.pass_id, event.batch_id, event.cost, event.metrics)
-        if isinstance(event, paddle.event.EndPass):
-            result = trainer.test(reader=paddle.reader.batched(
-                paddle.dataset.mnist.test(), batch_size=128))
-            print "Test with Pass %d, Cost %f, %s\n" % (
-                event.pass_id, result.cost, result.metrics)
-            lists.append((event.pass_id, result.cost,
-                          result.metrics['classification_error_evaluator']))
-
-    trainer.train(
-        reader=paddle.batch(
-            paddle.reader.shuffle(
-                paddle.dataset.mnist.train(), buf_size=8192),
-            batch_size=128),
-        event_handler=event_handler,
-        num_passes=100)
+lists = []
+
+def event_handler(event):
+    if isinstance(event, paddle.event.EndIteration):
+        if event.batch_id % 100 == 0:
+            print "Pass %d, Batch %d, Cost %f, %s" % (
+                event.pass_id, event.batch_id, event.cost, event.metrics)
+    if isinstance(event, paddle.event.EndPass):
+        result = trainer.test(reader=paddle.reader.batched(
+            paddle.dataset.mnist.test(), batch_size=128))
+        print "Test with Pass %d, Cost %f, %s\n" % (
+            event.pass_id, result.cost, result.metrics)
+        lists.append((event.pass_id, result.cost,
+                      result.metrics['classification_error_evaluator']))
+
+trainer.train(
+    reader=paddle.reader.batched(
+        paddle.reader.shuffle(
+            paddle.dataset.mnist.train(), buf_size=8192),
+        batch_size=128),
+    event_handler=event_handler,
+    num_passes=100)
 ```
 
 训练过程是完全自动的，event_handler里打印的日志类似如下所示：
 
 ```
-    # Pass 0, Batch 0, Cost 2.780790, {'classification_error_evaluator': 0.9453125}
-    # Pass 0, Batch 100, Cost 0.635356, {'classification_error_evaluator': 0.2109375}
-    # Pass 0, Batch 200, Cost 0.326094, {'classification_error_evaluator': 0.1328125}
-    # Pass 0, Batch 300, Cost 0.361920, {'classification_error_evaluator': 0.1015625}
-    # Pass 0, Batch 400, Cost 0.410101, {'classification_error_evaluator': 0.125}
-    # Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
+# Pass 0, Batch 0, Cost 2.780790, {'classification_error_evaluator': 0.9453125}
+# Pass 0, Batch 100, Cost 0.635356, {'classification_error_evaluator': 0.2109375}
+# Pass 0, Batch 200, Cost 0.326094, {'classification_error_evaluator': 0.1328125}
+# Pass 0, Batch 300, Cost 0.361920, {'classification_error_evaluator': 0.1015625}
+# Pass 0, Batch 400, Cost 0.410101, {'classification_error_evaluator': 0.125}
+# Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
 ```
 
 训练之后，检查模型的预测准确度。用 MNIST 训练的时候，一般 softmax回归模型的分类准确率为约为 92.34%，多层感知器为97.66%，卷积神经网络可以达到 99.20%。
diff --git a/recognize_digits/index.en.html b/recognize_digits/index.en.html
index 49fe293..f918bad 100644
--- a/recognize_digits/index.en.html
+++ b/recognize_digits/index.en.html
@@ -156,15 +156,8 @@ For more information, please refer to [Activation functions on Wikipedia](https:
 
 ## Data Preparation
 
-### Data Download
+PaddlePaddle provides a Python module, `paddle.dataset.mnist`, which downloads and caches the [MNIST dataset](http://yann.lecun.com/exdb/mnist/).  The cache is under `/home/username/.cache/paddle/dataset/mnist`:
 
-Execute the following command to download the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset and unzip. Add paths to the training set and the test set to train.list and test.list respectively for PaddlePaddle to read.
-
-```bash
-./data/get_mnist_data.sh
-```
-
-`gzip` downloaded data. The following files can be found in `data/raw_data`:
 
 |    File name          |       Description              |
 |----------------------|-------------------------|
@@ -173,283 +166,159 @@ Execute the following command to download the [MNIST](http://yann.lecun.com/exdb
 |t10k-images-idx3-ubyte |  Evaluation images, 10,000 |
 |t10k-labels-idx1-ubyte |  Evaluation labels, 10,000 |
 
-Users can randomly generate 10 images with the following script (Refer to Fig. 1.)
-
-```bash
-./load_data.py
-```
-
-### Provide Data to PaddlePaddle
-
-We use python interface to provide data to system. `mnist_provider.py` shows a complete example for training on MNIST data.
-
-```python
-# Define a py data provider
-@provider(
-    input_types={'pixel': dense_vector(28 * 28),
-                 'label': integer_value(10)})
-def process(settings, filename):  # settings is not used currently.
-		# Open image file
-    with open( filename + "-images-idx3-ubyte", "rb") as f:             
-		# Read first 4 parameters. magic is data format. n is number of data. rows and cols are number of rows and columns, respectively
-        magic, n, rows, cols = struct.upack(">IIII", f.read(16))        
-		# With empty string as a unit, read data one by one
-        images = np.fromfile(                                           
-            f, 'ubyte',
-            count=n * rows * cols).reshape(n, rows, cols).astype('float32')
-		# Normalize data of [0, 255] to [-1,1]
-        images = images / 255.0 * 2.0 - 1.0                             
-
-
-		# Open label file
-    with open( filename + "-labels-idx1-ubyte", "rb") as l:             
-		# Read first two parameters
-        magic, n = struct.upack(">II", l.read(8))                       
-		# With empty string as a unit, read data one by one
-        labels = np.fromfile(l, 'ubyte', count=n).astype("int")         
-
-    for i in xrange(n):
-        yield {"pixel": images[i, :], 'label': labels[i]}
-```
-
-
-## Model Configurations
-
-### Data Definition
-
-In the model configuration, use `define_py_data_sources2` to define reading of data from `dataprovider`. If this configuration is used for prediction, data definition is not necessary.
-
-```python
- if not is_predict:
-     data_dir = './data/'
-     define_py_data_sources2(
-         train_list=data_dir + 'train.list',
-         test_list=data_dir + 'test.list',
-         module='mnist_provider',
-         obj='process')
-```
 
-### Algorithm Configuration
+## Model Configuration
 
-Set training related parameters.
-
-- batch_size: use 128 samples in each training step.
-- learning_rate: determines step taken in each iteration, it determines how fast the model converges.
-- learning_method: use optimizer `MomentumOptimizer` for training. The parameter 0.9 indicates momentum keeps 0.9 of previous speed.
-- regularization: A method to prevent overfitting. Here L2 regularization is used.
+A PaddlePaddle program starts from importing the API package:
 
 ```python
-settings(
-    batch_size=128,
-    learning_rate=0.1 / 128.0,
-    learning_method=MomentumOptimizer(0.9),
-    regularization=L2Regularization(0.0005 * 128))
+import paddle.v2 as paddle
 ```
 
-### Model Architecture
+We want to use this program to demonstrate multiple kinds of models.  Let define each of them as a Python function:
 
-#### Overview
-
-First get reference labels from `data_layer`, and get classification results (predictions) from classifier. Here we provide three different classifiers. In training, we compute loss function, which is usually cross entropy for classification problem. In prediction, we can directly output the results (predictions).
-
-``` python
-data_size = 1 * 28 * 28
-label_size = 10
-img = data_layer(name='pixel', size=data_size)
-
-predict = softmax_regression(img) # Softmax Regression
-#predict = multilayer_perceptron(img) # Multilayer Perceptron
-#predict = convolutional_neural_network(img) #LeNet5 Convolutional Neural Network
- 
-if not is_predict:
-    lbl = data_layer(name="label", size=label_size)
-    inputs(img, lbl)
-    outputs(classification_cost(input=predict, label=lbl))
-else:
-    outputs(predict)
-```
-
-#### Softmax Regression
-
-One simple fully connected layer with softmax activation function outputs classification result.
+- softmax regression: the network has a fully-connection layer with softmax activation:
 
 ```python
 def softmax_regression(img):
-    predict = fc_layer(input=img, size=10, act=SoftmaxActivation())
+    predict = paddle.layer.fc(input=img,
+                              size=10,
+                              act=paddle.activation.Softmax())
     return predict
 ```
 
-#### MultiLayer Perceptron
-
-The following code implements a Multilayer Perceptron with two fully connected hidden layers and a ReLU activation function. The output layer has a Softmax activation function.
+- multi-layer perceptron: this network has two hidden fully-connected layers, one with LeRU and the other with softmax activation:
 
 ```python
 def multilayer_perceptron(img):
-    # First fully connected layer with ReLU
-    hidden1 = fc_layer(input=img, size=128, act=ReluActivation())
-    # Second fully connected layer with ReLU
-    hidden2 = fc_layer(input=hidden1, size=64, act=ReluActivation())
-    # Output layer as fully connected layer and softmax activation. The size must be 10.
-    predict = fc_layer(input=hidden2, size=10, act=SoftmaxActivation())
+    hidden1 = paddle.layer.fc(input=img, size=128, act=paddle.activation.Relu())
+    hidden2 = paddle.layer.fc(input=hidden1,
+                              size=64,
+                              act=paddle.activation.Relu())
+    predict = paddle.layer.fc(input=hidden2,
+                              size=10,
+                              act=paddle.activation.Softmax())
     return predict
 ```
 
-#### Convolutional Neural Network LeNet-5
-
-The following is the LeNet-5 network architecture. A 2D input image is first fed into two sets of convolutional layers and pooling layers, this result is then fed to a fully connected layer, and another fully connected layer with a softmax activation.
+- convolution network LeNet-5: the input image is fed through two convolution-pooling layer, a fully-connected layer, and the softmax output layer:
 
 ```python
 def convolutional_neural_network(img):
-    # First convolutional layer - pooling layer
-    conv_pool_1 = simple_img_conv_pool(
+
+    conv_pool_1 = paddle.networks.simple_img_conv_pool(
         input=img,
         filter_size=5,
         num_filters=20,
         num_channel=1,
         pool_size=2,
         pool_stride=2,
-        act=TanhActivation())
-    # Second convolutional layer - pooling layer
-    conv_pool_2 = simple_img_conv_pool(
+        act=paddle.activation.Tanh())
+
+    conv_pool_2 = paddle.networks.simple_img_conv_pool(
         input=conv_pool_1,
         filter_size=5,
         num_filters=50,
         num_channel=20,
         pool_size=2,
         pool_stride=2,
-        act=TanhActivation())
-    # Fully connected layer
-    fc1 = fc_layer(input=conv_pool_2, size=128, act=TanhActivation())
-    # Output layer as fully connected layer and softmax activation. The size must be 10.
-    predict = fc_layer(input=fc1, size=10, act=SoftmaxActivation())
-    return predict
-```
-
-## Training Model
-
-### Training Commands and Logs
-
-1.Configure `train.sh` to execute training:
+        act=paddle.activation.Tanh())
 
-```bash
-config=mnist_model.py                   # Select network in mnist_model.py
-output=./softmax_mnist_model            
-log=softmax_train.log                   
+    fc1 = paddle.layer.fc(input=conv_pool_2,
+                          size=128,
+                          act=paddle.activation.Tanh())
 
-paddle train \
---config=$config \                      # Scripts for network configuration.
---dot_period=10 \                       # After `dot_period` steps, print one `.`
---log_period=100 \						# Print a log every batchs
---test_all_data_in_one_period=1 \		# Whether to use all data in every test
---use_gpu=0 \							# Whether to use GPU
---trainer_count=1 \						# Number of CPU or GPU
---num_passes=100 \						# Passes for training (One pass uses all data.)
---save_dir=$output \					# Path to saved model
-2>&1 | tee $log
-
-python -m paddle.utils.plotcurve -i $log > plot.png
+    predict = paddle.layer.fc(input=fc1,
+                              size=10,
+                              act=paddle.activation.Softmax())
+    return predict
 ```
 
-After configuring parameters, execute `./train.sh`. Training log is as follows.
+PaddlePaddle provides a special layer `layer.data` for reading data. Let us create a data layer for reading images and connect it to a classification network created using one of above three functions.  We also need a cost layer for training the model.
 
-```
-I0117 12:52:29.628617  4538 TrainerInternal.cpp:165]  Batch=100 samples=12800 AvgCost=2.63996 CurrentCost=2.63996 Eval: classification_error_evaluator=0.241172  CurrentEval: classification_error_evaluator=0.241172 
-.........
-I0117 12:52:29.768741  4538 TrainerInternal.cpp:165]  Batch=200 samples=25600 AvgCost=1.74027 CurrentCost=0.840582 Eval: classification_error_evaluator=0.185234  CurrentEval: classification_error_evaluator=0.129297 
-.........
-I0117 12:52:29.916970  4538 TrainerInternal.cpp:165]  Batch=300 samples=38400 AvgCost=1.42119 CurrentCost=0.783026 Eval: classification_error_evaluator=0.167786  CurrentEval: classification_error_evaluator=0.132891 
-.........
-I0117 12:52:30.061213  4538 TrainerInternal.cpp:165]  Batch=400 samples=51200 AvgCost=1.23965 CurrentCost=0.695054 Eval: classification_error_evaluator=0.160039  CurrentEval: classification_error_evaluator=0.136797 
-......I0117 12:52:30.223270  4538 TrainerInternal.cpp:181]  Pass=0 Batch=469 samples=60000 AvgCost=1.1628 Eval: classification_error_evaluator=0.156233 
-I0117 12:52:30.366894  4538 Tester.cpp:109]  Test samples=10000 cost=0.50777 Eval: classification_error_evaluator=0.0978 
-```
-
-2.Use `plot_cost.py` to plot error curve during training.
+```python
+paddle.init(use_gpu=False, trainer_count=1)
 
-```bash
-python plot_cost.py softmax_train.log            
-```
+images = paddle.layer.data(
+    name='pixel', type=paddle.data_type.dense_vector(784))
+label = paddle.layer.data(
+    name='label', type=paddle.data_type.integer_value(10))
 
-3.Use `evaluate.py ` to select the best trained model.
+predict = softmax_regression(images)
+#predict = multilayer_perceptron(images) # uncomment for MLP
+#predict = convolutional_neural_network(images) # uncomment for LeNet5
 
-```bash
-python evaluate.py softmax_train.log
+cost = paddle.layer.classification_cost(input=predict, label=label)
 ```
 
-### Training Results for Softmax Regression
+Now, it is time to specify training parameters. The number 0.9 in the following `Momentum` optimizer means that 90% of the current the momentum comes from the momentum of the previous iteration.
 
-<p align="center">
-<img src="image/softmax_train_log_en.png" width="400px"><br/>
-Fig. 7 Softmax regression error curve<br/>
-</p>
+```python
+parameters = paddle.parameters.create(cost)
 
-Evaluation results of the models:
+optimizer = paddle.optimizer.Momentum(
+    learning_rate=0.1 / 128.0,
+    momentum=0.9,
+    regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
 
-```text
-Best pass is 00013, testing Avgcost is 0.484447
-The classification accuracy is 90.01%
+trainer = paddle.trainer.SGD(cost=cost,
+                             parameters=parameters,
+                             update_equation=optimizer)
 ```
 
-From the evaluation results, the best pass for softmax regression model is pass-00013, where the classification accuracy is 90.01%, and the last pass-00099 has an accuracy of 89.3%. From Fig. 7, we also see that the best accuracy may not appear in the last pass. This is because during training, the model may already arrive at a local optimum, and it just swings around nearby in the following passes, or it gets a lower local optimum.
+Then we specify the training data `paddle.dataset.movielens.train()` and testing data `paddle.dataset.movielens.test()`.  These two functions are *reader creators*, once called, returns a *reader*.  A reader is a Python function, which, once called, returns a Python generator, which yields instances of data.  
 
-### Results of Multilayer Perceptron
+Here `shuffle` is a reader decorator, which takes a reader A as its parameter, and returns a new reader B, where B calls A to read in `buffer_size` data instances everytime into a buffer, then shuffles and yield instances in the buffer.  If you want very shuffled data, try use a larger buffer size. 
 
-<p align="center">
-<img src="image/mlp_train_log_en.png" width="400px"><br/>
-Fig. 8. Multilayer Perceptron error curve<br/>
-</p>
+`batch` is a special decorator, whose input is a reader and output is a *batch reader*, which doesn't yield an instance at a time, but a minibatch.
 
-Evaluation results of the models：
-
-```text
-Best pass is 00085, testing Avgcost is 0.164746
-The classification accuracy is 94.95%
+```python
+lists = []
+
+def event_handler(event):
+    if isinstance(event, paddle.event.EndIteration):
+        if event.batch_id % 100 == 0:
+            print "Pass %d, Batch %d, Cost %f, %s" % (
+                event.pass_id, event.batch_id, event.cost, event.metrics)
+    if isinstance(event, paddle.event.EndPass):
+        result = trainer.test(reader=paddle.reader.batched(
+            paddle.dataset.mnist.test(), batch_size=128))
+        print "Test with Pass %d, Cost %f, %s\n" % (
+            event.pass_id, result.cost, result.metrics)
+        lists.append((event.pass_id, result.cost,
+                      result.metrics['classification_error_evaluator']))
+
+trainer.train(
+    reader=paddle.reader.batched(
+        paddle.reader.shuffle(
+            paddle.dataset.mnist.train(), buf_size=8192),
+        batch_size=128),
+    event_handler=event_handler,
+    num_passes=100)
 ```
 
-From the evaluation results, the final training accuracy is 94.95%. It is significantly better than the softmax regression model. This is because the softmax regression is simple, and it cannot fit complex data. The Multilayer Perceptron with hidden layers has better capacity to fit complex data than the softmax regression.
-
-### Training results for Convolutional Neural Network
-
-<p align="center">
-<img src="image/cnn_train_log_en.png" width="400px"><br/>
-Fig. 9. Convolutional Neural Network error curve<br/>
-</p>
+During training, `trainer.train` invokes `event_handler` for certain events. This gives us a chance to print the training progress.
 
-Results of model evaluation：
-
-```text
-Best pass is 00076, testing Avgcost is 0.0244684
-The classification accuracy is 99.20%
 ```
-
-From the evaluation result, the best accuracy of Convolutional Neural Network is 99.20%. So for image classification, a Convolutional Neural Network has better recognition results than a fully connected network. This is related to the local connection and parameter sharing of convolutional layers. In Fig. 9, the Convolutional Neural Network achieves good results in early steps, which indicates that it converges faster.
-
-## Application Model
-
-### Prediction Commands and Results
-Script `predict.py` can make prediction for trained models. For example, in softmax regression:
-
-```bash
-python predict.py -c mnist_model.py -d data/raw_data/ -m softmax_mnist_model/pass-00047
+# Pass 0, Batch 0, Cost 2.780790, {'classification_error_evaluator': 0.9453125}
+# Pass 0, Batch 100, Cost 0.635356, {'classification_error_evaluator': 0.2109375}
+# Pass 0, Batch 200, Cost 0.326094, {'classification_error_evaluator': 0.1328125}
+# Pass 0, Batch 300, Cost 0.361920, {'classification_error_evaluator': 0.1015625}
+# Pass 0, Batch 400, Cost 0.410101, {'classification_error_evaluator': 0.125}
+# Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
 ```
 
-- -c sets model architecture
-- -d sets data for prediction
-- -m sets model parameters, here the best trained model is used for prediction
-
-Follow the instructions to input image ID for prediction. The classifier can output probabilities for each digit, predictions with the highest probability, and ground truth label.
+After the training, we can check the model's prediction accuracy.
 
 ```
-Input image_id [0~9999]: 3
-Predicted probability of each digit:
-[[  1.00000000e+00   1.60381094e-28   1.60381094e-28   1.60381094e-28
-    1.60381094e-28   1.60381094e-28   1.60381094e-28   1.60381094e-28
-    1.60381094e-28   1.60381094e-28]]
-Predict Number: 0 
-Actual Number: 0
+# find the best pass
+best = sorted(lists, key=lambda list: float(list[1]))[0]
+print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
+print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
 ```
 
-From the result, this classifier recognizes the digit on the third image as digit 0 with near to 100% probability. This predicted result is consistent with the ground truth label.
+Usually, with MNIST data, the softmax regression model can get accuracy around 92.34%, MLP can get about 97.66%, and convolution network can get up to around 99.20%.  Convolution layers have been widely considered a great invention for image processsing.
+
 
 ## Conclusion
 This tutorial describes a few basic Deep Learning models viz. Softmax regression, Multilayer Perceptron Network and Convolutional Neural Network. The subsequent tutorials will derive more sophisticated models from these. So it is crucial to understand these models for future learning. When our model evolved from a simple softmax regression to slightly complex Convolutional Neural Network, the recognition accuracy on the MNIST data set achieved large improvement in accuracy. This is due to the Convolutional layers' local connections and parameter sharing. While learning new models in the future, we encourage the readers to understand the key ideas that lead a new model to improve results of an old one. Moreover, this tutorial introduced the basic flow of PaddlePaddle model design, starting with a dataprovider, model layer construction, to final training and prediction. Readers can leverage the flow used in this MNIST handwritten digit classification example and experiment with different data and network architectures to train models for classification tasks of their choice.
diff --git a/recognize_digits/index.html b/recognize_digits/index.html
index 32f4e6e..81b42c1 100644
--- a/recognize_digits/index.html
+++ b/recognize_digits/index.html
@@ -236,20 +236,19 @@ def convolutional_neural_network(img):
 接着，通过`layer.data`调用来获取数据，然后调用分类器（这里我们提供了三个不同的分类器）得到分类结果。训练时，对该结果计算其损失函数，分类问题常常选择交叉熵损失函数。
 
 ```python
-def main():
-    # 该模型运行在单个CPU上
-    paddle.init(use_gpu=False, trainer_count=1)
+# 该模型运行在单个CPU上
+paddle.init(use_gpu=False, trainer_count=1)
 
-    images = paddle.layer.data(
-        name='pixel', type=paddle.data_type.dense_vector(784))
-    label = paddle.layer.data(
-        name='label', type=paddle.data_type.integer_value(10))
+images = paddle.layer.data(
+    name='pixel', type=paddle.data_type.dense_vector(784))
+label = paddle.layer.data(
+    name='label', type=paddle.data_type.integer_value(10))
 
-    predict = softmax_regression(images) # Softmax回归
-    #predict = multilayer_perceptron(images) #多层感知器
-    #predict = convolutional_neural_network(images) #LeNet5卷积神经网络
+predict = softmax_regression(images) # Softmax回归
+#predict = multilayer_perceptron(images) #多层感知器
+#predict = convolutional_neural_network(images) #LeNet5卷积神经网络
 
-    cost = paddle.layer.classification_cost(input=predict, label=label)
+cost = paddle.layer.classification_cost(input=predict, label=label)
 ```
 
 然后，指定训练相关的参数。
@@ -258,84 +257,61 @@ def main():
 - 正则化（regularization）： 是防止网络过拟合的一种手段，此处采用L2正则化。
 
 ```python
-    parameters = paddle.parameters.create(cost)
+parameters = paddle.parameters.create(cost)
 
-    optimizer = paddle.optimizer.Momentum(
-        learning_rate=0.1 / 128.0,
-        momentum=0.9,
-        regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
+optimizer = paddle.optimizer.Momentum(
+    learning_rate=0.1 / 128.0,
+    momentum=0.9,
+    regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
 
-    trainer = paddle.trainer.SGD(cost=cost,
-                                 parameters=parameters,
-                                 update_equation=optimizer)
+trainer = paddle.trainer.SGD(cost=cost,
+                             parameters=parameters,
+                             update_equation=optimizer)
 ```
 
-下一步，我们开始训练过程。`paddle.dataset.movielens.train()`和`paddle.dataset.movielens.test()`分别做训练和测试数据集，每次训练使用的数据为128条。
+下一步，我们开始训练过程。`paddle.dataset.movielens.train()`和`paddle.dataset.movielens.test()`分别做训练和测试数据集。这两个函数各自返回一个reader——PaddlePaddle中的reader是一个Python函数，每次调用的时候返回一个Python yield generator。
 
-```python
-    lists = []
-
-    def event_handler(event):
-        if isinstance(event, paddle.event.EndIteration):
-            if event.batch_id % 100 == 0:
-                print "Pass %d, Batch %d, Cost %f, %s" % (
-                    event.pass_id, event.batch_id, event.cost, event.metrics)
-        if isinstance(event, paddle.event.EndPass):
-            result = trainer.test(reader=paddle.reader.batched(
-                paddle.dataset.mnist.test(), batch_size=128))
-            print "Test with Pass %d, Cost %f, %s\n" % (
-                event.pass_id, result.cost, result.metrics)
-            lists.append((event.pass_id, result.cost,
-                          result.metrics['classification_error_evaluator']))
-
-    trainer.train(
-        reader=paddle.reader.batched(
-            paddle.reader.shuffle(
-                paddle.dataset.mnist.train(), buf_size=8192),
-            batch_size=128),
-        event_handler=event_handler,
-        num_passes=100)
-```
+下面`shuffle`是一个reader decorator，它接受一个reader A，返回另一个reader B —— reader B 每次读入`buffer_size`条训练数据到一个buffer里，然后随机打乱其顺序，并且逐条输出。
 
-训练过程是完全自动的，event_handler里打印的日志类似如下所示：
+`batch`是一个特殊的decorator，它的输入是一个reader，输出是一个batched reader —— 在PaddlePaddle里，一个reader每次yield一条训练数据，而一个batched reader每次yield一个minbatch。
 
 ```python
-    # Pass 0, Batch 0, Cost 2.780790, {'classification_error_evaluator': 0.9453125}
-    # Pass 0, Batch 100, Cost 0.635356, {'classification_error_evaluator': 0.2109375}
-    # Pass 0, Batch 200, Cost 0.326094, {'classification_error_evaluator': 0.1328125}
-    # Pass 0, Batch 300, Cost 0.361920, {'classification_error_evaluator': 0.1015625}
-    # Pass 0, Batch 400, Cost 0.410101, {'classification_error_evaluator': 0.125}
-    # Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
+lists = []
+
+def event_handler(event):
+    if isinstance(event, paddle.event.EndIteration):
+        if event.batch_id % 100 == 0:
+            print "Pass %d, Batch %d, Cost %f, %s" % (
+                event.pass_id, event.batch_id, event.cost, event.metrics)
+    if isinstance(event, paddle.event.EndPass):
+        result = trainer.test(reader=paddle.reader.batched(
+            paddle.dataset.mnist.test(), batch_size=128))
+        print "Test with Pass %d, Cost %f, %s\n" % (
+            event.pass_id, result.cost, result.metrics)
+        lists.append((event.pass_id, result.cost,
+                      result.metrics['classification_error_evaluator']))
+
+trainer.train(
+    reader=paddle.reader.batched(
+        paddle.reader.shuffle(
+            paddle.dataset.mnist.train(), buf_size=8192),
+        batch_size=128),
+    event_handler=event_handler,
+    num_passes=100)
 ```
 
-最后，选出最佳模型，并评估其效果。
-
-```python
-    # find the best pass
-    best = sorted(lists, key=lambda list: float(list[1]))[0]
-    print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
-    print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
-```
-- softmax回归模型：分类效果最好的时候是pass-34，分类准确率为92.34%。
+训练过程是完全自动的，event_handler里打印的日志类似如下所示：
 
-```python
-    # Best pass is 34, testing Avgcost is 0.275004139346
-    # The classification accuracy is 92.34%
 ```
-
-- 多层感知器：最终训练的准确率为97.66%，相比于softmax回归模型有了显著的提升。原因是softmax回归模型较为简单，无法拟合更为复杂的数据，而加入了隐藏层之后的多层感知器则具有更强的拟合能力。
-
-```python
-    # Best pass is 85, testing Avgcost is 0.0784368447196
-    # The classification accuracy is 97.66%
+# Pass 0, Batch 0, Cost 2.780790, {'classification_error_evaluator': 0.9453125}
+# Pass 0, Batch 100, Cost 0.635356, {'classification_error_evaluator': 0.2109375}
+# Pass 0, Batch 200, Cost 0.326094, {'classification_error_evaluator': 0.1328125}
+# Pass 0, Batch 300, Cost 0.361920, {'classification_error_evaluator': 0.1015625}
+# Pass 0, Batch 400, Cost 0.410101, {'classification_error_evaluator': 0.125}
+# Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
 ```
 
-- 卷积神经网络：最好分类准确率达到惊人的99.20%。说明对于图像问题而言，卷积神经网络能够比一般的全连接网络达到更好的识别效果，而这与卷积层具有局部连接和共享权重的特性是分不开的。同时，从训练日志中可以看到，卷积神经网络在很早的时候就能达到很好的效果，说明其收敛速度非常快。
-
-```python
-    # Best pass is 76, testing Avgcost is 0.0244684
-    # The classification accuracy is 99.20%
-```
+训练之后，检查模型的预测准确度。用 MNIST 训练的时候，一般 softmax回归模型的分类准确率为约为 92.34%，多层感知器为97.66%，卷积神经网络可以达到 99.20%。
 
 ## 总结
 
diff --git a/recognize_digits/train.py b/recognize_digits/train.py
new file mode 100644
index 0000000..7ee1c83
--- /dev/null
+++ b/recognize_digits/train.py
@@ -0,0 +1,111 @@
+import paddle.v2 as paddle
+
+
+def softmax_regression(img):
+    predict = paddle.layer.fc(input=img,
+                              size=10,
+                              act=paddle.activation.Softmax())
+    return predict
+
+
+def multilayer_perceptron(img):
+    # The first fully-connected layer
+    hidden1 = paddle.layer.fc(input=img, size=128, act=paddle.activation.Relu())
+    # The second fully-connected layer and the according activation function
+    hidden2 = paddle.layer.fc(input=hidden1,
+                              size=64,
+                              act=paddle.activation.Relu())
+    # The thrid fully-connected layer, note that the hidden size should be 10,
+    # which is the number of unique digits
+    predict = paddle.layer.fc(input=hidden2,
+                              size=10,
+                              act=paddle.activation.Softmax())
+    return predict
+
+
+def convolutional_neural_network(img):
+    # first conv layer
+    conv_pool_1 = paddle.networks.simple_img_conv_pool(
+        input=img,
+        filter_size=5,
+        num_filters=20,
+        num_channel=1,
+        pool_size=2,
+        pool_stride=2,
+        act=paddle.activation.Tanh())
+    # second conv layer
+    conv_pool_2 = paddle.networks.simple_img_conv_pool(
+        input=conv_pool_1,
+        filter_size=5,
+        num_filters=50,
+        num_channel=20,
+        pool_size=2,
+        pool_stride=2,
+        act=paddle.activation.Tanh())
+    # The first fully-connected layer
+    fc1 = paddle.layer.fc(input=conv_pool_2,
+                          size=128,
+                          act=paddle.activation.Tanh())
+    # The softmax layer, note that the hidden size should be 10,
+    # which is the number of unique digits
+    predict = paddle.layer.fc(input=fc1,
+                              size=10,
+                              act=paddle.activation.Softmax())
+    return predict
+
+
+paddle.init(use_gpu=False, trainer_count=1)
+
+# define network topology
+images = paddle.layer.data(
+    name='pixel', type=paddle.data_type.dense_vector(784))
+label = paddle.layer.data(name='label', type=paddle.data_type.integer_value(10))
+
+# Here we can build the prediction network in different ways. Please
+# choose one by uncomment corresponding line.
+predict = softmax_regression(images)
+#predict = multilayer_perceptron(images)
+#predict = convolutional_neural_network(images)
+
+cost = paddle.layer.classification_cost(input=predict, label=label)
+
+parameters = paddle.parameters.create(cost)
+
+optimizer = paddle.optimizer.Momentum(
+    learning_rate=0.1 / 128.0,
+    momentum=0.9,
+    regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
+
+trainer = paddle.trainer.SGD(cost=cost,
+                             parameters=parameters,
+                             update_equation=optimizer)
+
+lists = []
+
+
+def event_handler(event):
+    if isinstance(event, paddle.event.EndIteration):
+        if event.batch_id % 100 == 0:
+            print "Pass %d, Batch %d, Cost %f, %s" % (
+                event.pass_id, event.batch_id, event.cost, event.metrics)
+    if isinstance(event, paddle.event.EndPass):
+        result = trainer.test(reader=paddle.reader.batched(
+            paddle.dataset.mnist.test(), batch_size=128))
+        print "Test with Pass %d, Cost %f, %s\n" % (event.pass_id, result.cost,
+                                                    result.metrics)
+        lists.append((event.pass_id, result.cost,
+                      result.metrics['classification_error_evaluator']))
+
+
+trainer.train(
+    reader=paddle.reader.batched(
+        paddle.reader.shuffle(
+            paddle.dataset.mnist.train(), buf_size=8192),
+        batch_size=128),
+    event_handler=event_handler,
+    num_passes=100)
+
+# find the best pass
+best = sorted(lists, key=lambda list: float(list[1]))[0]
+print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
+print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
diff --git a/recommender_system/index.en.html b/recommender_system/index.en.html
index c4319f4..b5a4cfd 100644
--- a/recommender_system/index.en.html
+++ b/recommender_system/index.en.html
@@ -111,7 +111,7 @@ Given the feature vectors of users and movies, we compute the relevance using co
 
 <p align="center">
 
-<img src="image/rec_regression_network.png" width="90%" ><br/>
+<img src="image/rec_regression_network_en.png" width="90%" ><br/>
 Figure 3. A hybrid recommendation model.
 </p> 
 
diff --git a/word2vec/index.en.html b/word2vec/index.en.html
index b9a7b10..f20c2b3 100644
--- a/word2vec/index.en.html
+++ b/word2vec/index.en.html
@@ -194,7 +194,7 @@ As illustrated in the figure above, skip-gram model maps the word embedding of t
 
 ## Model Configuration
 <p align="center">	
-	<img src="image/ngram.png" width=400><br/>
+	<img src="image/ngram.en.png" width=400><br/>
 	Figure 5. N-gram neural network model in model configuration
 </p>
 
diff --git a/word2vec/index.html b/word2vec/index.html
index 7814ee5..dbc9c53 100644
--- a/word2vec/index.html
+++ b/word2vec/index.html
@@ -182,7 +182,7 @@ CBOW的好处是对上下文词语的分布在词向量上进行了平滑，去
 
 ## 数据准备
 
-### 数据介绍与下载
+### 数据介绍
 
 本教程使用Penn Tree Bank (PTB)数据集。PTB数据集较小，训练速度快，应用于Mikolov的公开语言模型训练工具\[[2](#参考文献)\]中。其统计情况如下：
 
@@ -206,109 +206,24 @@ CBOW的好处是对上下文词语的分布在词向量上进行了平滑，去
 </table>
 </p>
 
-执行以下命令，可下载该数据集，并分别将训练数据和验证数据输入`train.list`和`test.list`文件中，供PaddlePaddle训练时使用。
-
-```bash
-./data/getdata.sh
-```
-
 	
-### 提供数据给PaddlePaddle
-
-1. 使用initializer函数进行dataprovider的初始化，包括字典的建立（build_dict函数中）和PaddlePaddle输入字段的格式定义。注意：这里N为n-gram模型中的`n`, 本章代码中，定义$N=5$, 表示在PaddlePaddle训练时，每条数据的前4个词用来预测第5个词。大家也可以根据自己的数据和需求自行调整N，但调整的同时要在模型配置文件中加入/减少相应输入字段。
-
-    ```python
-    from paddle.trainer.PyDataProvider2 import *
-    import collections
-    import logging
-    import pdb
-    
-    logging.basicConfig(
-        format='[%(levelname)s %(asctime)s %(filename)s:%(lineno)s] %(message)s', )
-    logger = logging.getLogger('paddle')
-    logger.setLevel(logging.INFO)
-    
-    N = 5  # Ngram
-    cutoff = 50  # select words with frequency > cutoff to dictionary
-    def build_dict(ftrain, fdict):
-    	sentences = []
-        with open(ftrain) as fin:
-            for line in fin:
-                line = ['<s>'] + line.strip().split() + ['<e>']
-                sentences += line
-        wordfreq = collections.Counter(sentences)
-        wordfreq = filter(lambda x: x[1] > cutoff, wordfreq.items())
-        dictionary = sorted(wordfreq, key = lambda x: (-x[1], x[0]))
-        words, _ = list(zip(*dictionary))
-        for word in words:
-            print >> fdict, word
-        word_idx = dict(zip(words, xrange(len(words))))
-        logger.info("Dictionary size=%s" %len(words))
-        return word_idx
-    
-    def initializer(settings, srcText, dictfile, **xargs):
-        with open(dictfile, 'w') as fdict:
-            settings.dicts = build_dict(srcText, fdict)
-        input_types = []
-        for i in xrange(N):
-            input_types.append(integer_value(len(settings.dicts)))
-        settings.input_types = input_types
-    ```
-
-2. 使用process函数中将数据逐一提供给PaddlePaddle。具体来说，将每句话前面补上N-1个开始符号 `<s>`, 末尾补上一个结束符号 `<e>`，然后以N为窗口大小，从头到尾每次向右滑动窗口并生成一条数据。
-
-    ```python
-    @provider(init_hook=initializer)
-    def process(settings, filename):
-        UNKID = settings.dicts['<unk>']
-        with open(filename) as fin:
-            for line in fin:
-                line = ['<s>']*(N-1)  + line.strip().split() + ['<e>']
-                line = [settings.dicts.get(w, UNKID) for w in line]
-                for i in range(N, len(line) + 1):
-                    yield line[i-N: i]
-    ```
-    
-    如"I have a dream" 一句提供了5条数据:
-
-    > `<s> <s> <s> <s> I` <br>
-    > `<s> <s> <s> I have` <br>
-    > `<s> <s> I have a`  <br>
-    > `<s> I have a dream` <br>
-    > `I have a dream <e>` <br>
-
-
-## 模型配置说明
-
-### 数据定义
-
-通过`define_py_data_sources2`函数从dataprovider中读入数据，其中args指定了训练文本(srcText)和词汇表(dictfile)。
-
-```python
-from paddle.trainer_config_helpers import *
-import math
+### 数据预处理
 
-args = {'srcText': 'data/simple-examples/data/ptb.train.txt',
-        'dictfile': 'data/vocabulary.txt'}
-		
-define_py_data_sources2(
-    train_list="data/train.list",
-    test_list="data/test.list",
-    module="dataprovider",
-    obj="process",
-    args=args)
-```
+本章训练的是5-gram模型，表示在PaddlePaddle训练时，每条数据的前4个词用来预测第5个词。PaddlePaddle提供了对应PTB数据集的python包`paddle.dataset.imikolov`，自动做数据的下载与预处理，方便大家使用。
 
-### 算法配置
+预处理会把数据集中的每一句话前后加上开始符号`<s>`以及结束符号`<e>`。然后依据窗口大小（本教程中为5），从头到尾每次向右滑动窗口并生成一条数据。
 
-在这里，我们指定了模型的训练参数, L2正则项系数、学习率和batch size。
+如"I have a dream that one day" 一句提供了5条数据：
 
-```python
-settings(
-    batch_size=100, regularization=L2Regularization(8e-4), learning_rate=3e-3)
+```text
+<s> I have a dream
+I have a dream that
+have a dream that one
+a dream that one day
+dream that one day <e>
 ```
 
-### 模型结构
+## 编程实现
 
 本配置的模型结构如下图所示：
 
@@ -317,94 +232,132 @@ settings(
 	图5. 模型配置中的N-gram神经网络模型
 </p>
 
-1. 定义参数维度和和数据输入。
-
-    ```python
-    dictsize = 1953 # 字典大小
-    embsize = 32 # 词向量维度
-    hiddensize = 256 # 隐层维度
-    
-    firstword = data_layer(name = "firstw", size = dictsize)
-    secondword = data_layer(name = "secondw", size = dictsize)
-    thirdword = data_layer(name = "thirdw", size = dictsize)
-    fourthword = data_layer(name = "fourthw", size = dictsize)
-    nextword = data_layer(name = "fifthw", size = dictsize)
-    ```
-
-2. 将$w_t$之前的$n-1$个词 $w_{t-n+1},...w_{t-1}$，通过$|V|\times D$的矩阵映射到D维词向量（本例中取D=32）。
+首先，加载所需要的包：
+
+```python
+import math
+import paddle.v2 as paddle
+```
+
+然后，定义参数：
+```python
+embsize = 32 # 词向量维度
+hiddensize = 256 # 隐层维度
+N = 5 # 训练5-Gram
+```
+
+接着，定义网络结构：
+
+- 将$w_t$之前的$n-1$个词 $w_{t-n+1},...w_{t-1}$，通过$|V|\times D$的矩阵映射到D维词向量（本例中取D=32）。
 	
-	```python	
-	def wordemb(inlayer):
-		wordemb = table_projection(
-        input = inlayer,
-        size = embsize,
-        param_attr=ParamAttr(name = "_proj",
-            initial_std=0.001, # 参数初始化标准差
-            l2_rate= 0,))      # 词向量不需要稀疏化，因此其l2_rate设为0
+```python	
+def wordemb(inlayer):
+    wordemb = paddle.layer.table_projection(
+        input=inlayer,
+        size=embsize,
+        param_attr=paddle.attr.Param(
+            name="_proj",
+            initial_std=0.001,
+            learning_rate=1,
+            l2_rate=0, ))
     return wordemb
+```
 
-	Efirst = wordemb(firstword)
-	Esecond = wordemb(secondword)
-	Ethird = wordemb(thirdword)
-	Efourth = wordemb(fourthword)
-	```
-
-3. 接着，将这n-1个词向量经过concat_layer连接成一个大向量作为历史文本特征。
-
-	```python
-	contextemb = concat_layer(input = [Efirst, Esecond, Ethird, Efourth])
-	```
-4. 然后，将历史文本特征经过一个全连接得到文本隐层特征。
-
-    ```python
-	hidden1 = fc_layer(
-	        input = contextemb,
-	        size = hiddensize,
-	        act = SigmoidActivation(),
-	        layer_attr = ExtraAttr(drop_rate=0.5),
-	        bias_attr = ParamAttr(learning_rate = 2),
-	        param_attr = ParamAttr(
-	            initial_std = 1./math.sqrt(embsize*8),
-	            learning_rate = 1))
-    ```
-	
-5. 最后，将文本隐层特征，再经过一个全连接，映射成一个$|V|$维向量，同时通过softmax归一化得到这`|V|`个词的生成概率。
-
-    ```python
-	# use context embedding to predict nextword
-	predictword = fc_layer(
-	        input = hidden1,
-	        size = dictsize,
-	        bias_attr = ParamAttr(learning_rate = 2),
-	        act = SoftmaxActivation())
-	```
-
-6. 网络的损失函数为多分类交叉熵，可直接调用`classification_cost`函数。
-
-	```python
-	cost = classification_cost(
-	        input = predictword,
-	        label = nextword)
-	# network input and output
-	outputs(cost)
-	```
+- 定义输入层接受的数据类型以及名字。
+
+```python
+def main():
+    paddle.init(use_gpu=False, trainer_count=1) # 初始化PaddlePaddle
+    word_dict = paddle.dataset.imikolov.build_dict()
+    dict_size = len(word_dict)
+	# 每个输入层都接受整形数据，这些数据的范围是[0, dict_size)
+    firstword = paddle.layer.data(
+        name="firstw", type=paddle.data_type.integer_value(dict_size))
+    secondword = paddle.layer.data(
+        name="secondw", type=paddle.data_type.integer_value(dict_size))
+    thirdword = paddle.layer.data(
+        name="thirdw", type=paddle.data_type.integer_value(dict_size))
+    fourthword = paddle.layer.data(
+        name="fourthw", type=paddle.data_type.integer_value(dict_size))
+    nextword = paddle.layer.data(
+        name="fifthw", type=paddle.data_type.integer_value(dict_size))
+
+    Efirst = wordemb(firstword)
+    Esecond = wordemb(secondword)
+    Ethird = wordemb(thirdword)
+    Efourth = wordemb(fourthword)
+```
+
+- 将这n-1个词向量经过concat_layer连接成一个大向量作为历史文本特征。
+
+```python
+    contextemb = paddle.layer.concat(input=[Efirst, Esecond, Ethird, Efourth])
+```
+
+- 将历史文本特征经过一个全连接得到文本隐层特征。
+
+```python
+    hidden1 = paddle.layer.fc(input=contextemb,
+                              size=hiddensize,
+                              act=paddle.activation.Sigmoid(),
+                              layer_attr=paddle.attr.Extra(drop_rate=0.5),
+                              bias_attr=paddle.attr.Param(learning_rate=2),
+                              param_attr=paddle.attr.Param(
+                                  initial_std=1. / math.sqrt(embsize * 8),
+                                  learning_rate=1))
+```
 	
-##训练模型
+- 将文本隐层特征，再经过一个全连接，映射成一个$|V|$维向量，同时通过softmax归一化得到这`|V|`个词的生成概率。
+
+```python
+    predictword = paddle.layer.fc(input=hidden1,
+                                  size=dict_size,
+                                  bias_attr=paddle.attr.Param(learning_rate=2),
+                                  act=paddle.activation.Softmax())
+```
 
-模型训练命令为`./train.sh`。脚本内容如下，其中指定了总共需要执行30个pass。
+- 网络的损失函数为多分类交叉熵，可直接调用`classification_cost`函数。
 
-```bash
-paddle train \
-       --config ngram.py \
-       --use_gpu=1 \
-       --dot_period=100 \
-       --log_period=3000 \
-       --test_period=0 \
-       --save_dir=model \
-       --num_passes=30
+```python
+cost = paddle.layer.classification_cost(input=predictword, label=nextword)
+```
+
+然后，指定训练相关的参数：
+
+- 训练方法（optimizer)： 代表训练过程在更新权重时采用动量优化器，本教程使用Adam优化器。
+- 训练速度（learning_rate）： 迭代的速度，与网络的训练收敛速度有关系。
+- 正则化（regularization）： 是防止网络过拟合的一种手段，此处采用L2正则化。
+
+```python
+    parameters = paddle.parameters.create(cost)
+    adam_optimizer = paddle.optimizer.Adam(
+        learning_rate=3e-3,
+        regularization=paddle.optimizer.L2Regularization(8e-4))
+    trainer = paddle.trainer.SGD(cost, parameters, adam_optimizer)
+```
+
+下一步，我们开始训练过程。`paddle.dataset.imikolov.train()`和`paddle.dataset.imikolov.test()`分别做训练和测试数据集。这两个函数各自返回一个reader——PaddlePaddle中的reader是一个Python函数，每次调用的时候返回一个Python generator。
+
+`paddle.batch`的输入是一个reader，输出是一个batched reader —— 在PaddlePaddle里，一个reader每次yield一条训练数据，而一个batched reader每次yield一个minbatch。
+
+```python
+    def event_handler(event):
+        if isinstance(event, paddle.event.EndIteration):
+            if event.batch_id % 100 == 0:
+                result = trainer.test(
+                    paddle.batch(
+                        paddle.dataset.imikolov.test(word_dict, N), 32))
+                print "Pass %d, Batch %d, Cost %f, %s, Testing metrics %s" % (
+                    event.pass_id, event.batch_id, event.cost, event.metrics,
+                    result.metrics)
+
+    trainer.train(
+        paddle.batch(paddle.dataset.imikolov.train(word_dict, N), 32),
+        num_passes=30,
+        event_handler=event_handler)
 ```
 
-一个pass的训练日志如下所示：
+训练过程是完全自动的，event_handler里打印的日志类似如下所示：
 
 ```text
 .............................
-- 
GitLab