Merge branch 'develop' of https://github.com/PaddlePaddle/book into...

Merge branch 'develop' of https://github.com/PaddlePaddle/book into fix_a_display_error_in_image_classification

.tools/build_docker.sh

+#!/bin/bash
+cur_path="$(cd "$(dirname "$0")" && pwd -P)"
+cd $cur_path/../
+
+#convert md to ipynb
+.tools/convert-markdown-into-ipynb-and-test.sh
+
+paddle_version=0.10.0rc2
+
+#generate docker file
+if [ ${USE_UBUNTU_REPO_MIRROR} ]; then
+  UPDATE_MIRROR_CMD="sed 's@http:\/\/archive.ubuntu.com\/ubuntu\/@mirror:\/\/mirrors.ubuntu.com\/mirrors.txt@' -i /etc/apt/sources.list && \\"
+else
+  UPDATE_MIRROR_CMD="\\"
+fi
+
+mkdir -p build
+cat > build/Dockerfile <<EOF
+FROM paddlepaddle/paddle:${paddle_version}
+MAINTAINER PaddlePaddle Authors <paddle-dev@baidu.com>
+
+RUN ${UPDATE_MIRROR_CMD}
+        apt-get install locales
+RUN localedef -f UTF-8 -i en_US en_US.UTF-8
+
+RUN  apt-get -y install gcc && \
+        apt-get -y clean
+
+RUN pip install -U matplotlib jupyter numpy requests scipy
+
+COPY . /book
+RUN rm -rf /book/build
+
+EXPOSE 8888
+CMD ["sh", "-c", "jupyter notebook --ip=0.0.0.0 --no-browser --NotebookApp.token='' --NotebookApp.disable_check_xsrf=True /book/"]
+EOF
+
+#build docker image
+echo "paddle_version:"$paddle_version
+docker build --no-cache -t paddlepaddle/book:${paddle_version}  -t paddlepaddle/book:latest  -f ./build/Dockerfile .

.tools/convert-markdown-into-ipynb-and-test.sh

@@ -5,9 +5,9 @@ if [ $? -ne 0 ]; then
     exit 1
 fi
 
-GOPATH=/tmp/go go get -u github.com/wangkuiyi/ipynb/markdown-to-ipynb
+GOPATH=~/.go go get -u github.com/wangkuiyi/ipynb/markdown-to-ipynb
 
-cur_path=$(dirname $(readlink -f $0))
+cur_path="$(cd "$(dirname "$0")" && pwd -P)"
 cd $cur_path/../
 
 #convert md to ipynb

image_classification/README.en.md → 03.image_classification/README.en.md

@@ -148,9 +148,9 @@ Figure 10. ResNet model for ImageNet
 
 ## Dataset
 
-Commonly used public datasets for image classification are CIFAR(https://www.cs.toronto.edu/~kriz/cifar.html), ImageNet(http://image-net.org/), COCO(http://mscoco.org/), etc. Those used for fine-grained image classification are CUB-200-2011(http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), Stanford Dog(http://vision.stanford.edu/aditya86/ImageNetDogs/), Oxford-flowers(http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
+Commonly used public datasets for image classification are [CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html), [ImageNet](http://image-net.org/), [COCO](http://mscoco.org/), etc. Those used for fine-grained image classification are [CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), [Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/), [Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
 
-Since ImageNet is too large to be downloaded and trained efficiently, we use CIFAR-10 (https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
+Since ImageNet is too large to be downloaded and trained efficiently, we use [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
 
 <p align="center">
 <img src="image/cifar.png" width="350"><br/>

image_classification/README.md → 03.image_classification/README.md

@@ -135,7 +135,7 @@ ResNet(Residual Network) \[[15](#参考文献)\] 是2015年ImageNet图像分类
 
 ## 数据准备
 
-通用图像分类公开的标准数据集常用的有[CIFAR](<https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
+通用图像分类公开的标准数据集常用的有[CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
 
 由于ImageNet数据集较大，下载和训练较慢，为了方便大家学习，我们使用[CIFAR10](<https://www.cs.toronto.edu/~kriz/cifar.html>)数据集。CIFAR10数据集包含60,000张32x32的彩色图片，10个类别，每个类包含6,000张。其中50,000张图片作为训练集，10000张作为测试集。图11从每个类别中随机抽取了10张图片，展示了所有的类别。
 

image_classification/index.en.html → 03.image_classification/index.en.html

@@ -190,9 +190,9 @@ Figure 10. ResNet model for ImageNet
 
 ## Dataset
 
-Commonly used public datasets for image classification are CIFAR(https://www.cs.toronto.edu/~kriz/cifar.html), ImageNet(http://image-net.org/), COCO(http://mscoco.org/), etc. Those used for fine-grained image classification are CUB-200-2011(http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), Stanford Dog(http://vision.stanford.edu/aditya86/ImageNetDogs/), Oxford-flowers(http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
+Commonly used public datasets for image classification are [CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html), [ImageNet](http://image-net.org/), [COCO](http://mscoco.org/), etc. Those used for fine-grained image classification are [CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), [Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/), [Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
 
-Since ImageNet is too large to be downloaded and trained efficiently, we use CIFAR-10 (https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
+Since ImageNet is too large to be downloaded and trained efficiently, we use [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
 
 <p align="center">
 <img src="image/cifar.png" width="350"><br/>

image_classification/index.html → 03.image_classification/index.html

@@ -177,7 +177,7 @@ ResNet(Residual Network) \[[15](#参考文献)\] 是2015年ImageNet图像分类
 
 ## 数据准备
 
-通用图像分类公开的标准数据集常用的有[CIFAR](<https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
+通用图像分类公开的标准数据集常用的有[CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
 
 由于ImageNet数据集较大，下载和训练较慢，为了方便大家学习，我们使用[CIFAR10](<https://www.cs.toronto.edu/~kriz/cifar.html>)数据集。CIFAR10数据集包含60,000张32x32的彩色图片，10个类别，每个类包含6,000张。其中50,000张图片作为训练集，10000张作为测试集。图11从每个类别中随机抽取了10张图片，展示了所有的类别。
 

understand_sentiment/README.en.md → 05.understand_sentiment/README.en.md

@@ -334,7 +334,7 @@ def event_handler(event):
             sys.stdout.write('.')
             sys.stdout.flush()
     if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(reader=test_reader, reader_dict=reader_dict)
+        result = trainer.test(reader=test_reader, feeding=feeding)
         print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
 ```
 

understand_sentiment/index.en.html → 05.understand_sentiment/index.en.html

@@ -376,7 +376,7 @@ def event_handler(event):
             sys.stdout.write('.')
             sys.stdout.flush()
     if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(reader=test_reader, reader_dict=reader_dict)
+        result = trainer.test(reader=test_reader, feeding=feeding)
         print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
 ```
 

label_semantic_roles/README.en.md → 06.label_semantic_roles/README.en.md

 # Semantic Role Labeling
 
-Source code of this chapter is in [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles).
+The source code of this chapter is live on [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles).
 
 For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
 ## 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 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.
+Natural language analysis techniques consist of lexical, syntactic, and semantic analysis. **Semantic Role Labeling (SRL)** is an instance of **Shallow Semantic Analysis**.
 
-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.
+In a sentence, a **predicate** states a property or a characterization of a *subject*, such as what it does and what it is like. The predicate represents the core of an event, whereas the words accompanying the predicate are **arguments**. A **semantic role** refers to the abstract role an argument of a predicate take on in the event, including *agent*, *patient*, *theme*, *experiencer*, *beneficiary*, *instrument*, *location*, *goal*, and *source*.
 
-$$\mbox{[小明]}_{\mbox{Agent}}\mbox{[昨天]}_{\mbox{Time}}\mbox{[晚上]}_\mbox{Time}\mbox{在[公园]}_{\mbox{Location}}\mbox{[遇到]}_{\mbox{Predicate}}\mbox{了[小红]}_{\mbox{Patient}}\mbox{。}$$
+In the following example of a Chinese sentence, "to encounter" is the predicate (*pred*); "Ming" is the *agent*; "Hong" is the *patient*; "yesterday" and "evening" are the *time*; finally, "the park" is the *location*.
 
-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.
+$$\mbox{[小明 Ming]}_{\mbox{Agent}}\mbox{[昨天 yesterday]}_{\mbox{Time}}\mbox{[晚上 evening]}_\mbox{Time}\mbox{在[公园 a park]}_{\mbox{Location}}\mbox{[遇到 to encounter]}_{\mbox{Predicate}}\mbox{了[小红 Hong]}_{\mbox{Patient}}\mbox{。}$$
 
-Standard SRL system mostly builds on top of Syntactic Analysis and contains five steps:
+Instead of analyzing the semantic information, **Semantic Role Labeling** (**SRL**) identifies the relation between the predicate and the other constituents surrounding it. The predicate-argument structures are labeled as specific semantic roles. A wide range of natural language understanding tasks, including *information extraction*, *discourse analysis*, and *deepQA*. Research usually assumes a predicate of a sentence to be specified; the only task is to identify its arguments and their semantic roles.
 
-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 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).
+Conventional SRL systems mostly build on top of syntactic analysis, usually consisting of five steps:
+
+1. Construct a syntax tree, as shown in Fig. 1
+2. Identity the candidate arguments of the given predicate on the tree.
+3. Prune the most unlikely candidate arguments.
+4. Identify the real arguments, often by a binary classifier.
+5. Multi-classify on results from step 4 to label the semantic roles. Steps 2 and 3 usually introduce hand-designed features based on syntactic analysis (step 1).
 
 
 <div  align="center">
 <img src="image/dependency_parsing_en.png" width = "80%" align=center /><br>
-Fig 1. Syntactic parse tree
+Fig 1. Syntax tree
 </div>
 
 
-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.
+However, a complete syntactic analysis requires identifying the relation among all constituents. Thus, the accuracy of SRL is sensitive to the preciseness of the syntactic analysis, making SRL challenging. To reduce its complexity and obtain some information on the syntactic structures, we often use *shallow syntactic analysis* a.k.a. partial parsing or chunking. Unlike complete syntactic analysis, which requires the construction of the complete parsing tree, *Shallow Syntactic Analysis* only requires identifying some independent constituents with relatively simple structures, such as verb phrases (chunk). To avoid difficulties in constructing a syntax tree with high accuracy, some work\[[1](#Reference)\] proposed semantic chunking-based SRL methods, which reduces SRL into a sequence tagging problem. Sequence tagging tasks classify syntactic chunks using **BIO representation**. For syntactic chunks forming role A, its first chunk receives the B-A tag (Begin) and the remaining ones receive the tag I-A (Inside); in the end, the chunks left out receive the tag O.
 
 The BIO representation of above example is shown in Fig.1.
 
 <div  align="center">
 <img src="image/bio_example_en.png" width = "90%"  align=center /><br>
-Fig 2. BIO represention
+Fig 2. BIO representation
 </div>
 
-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.
+This example illustrates the simplicity of sequence tagging, since
+
+1. It only relies on shallow syntactic analysis, reduces the precision requirement of syntactic analysis;
+2. Pruning the candidate arguments is no longer necessary;
+3. Arguments are identified and tagged at the same time. Simplifying the workflow reduces the risk of accumulating errors; oftentimes, methods that unify multiple steps boost performance.
 
 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.
 
@@ -48,15 +54,19 @@ Recurrent Neural Networks are important tools for sequence modeling and have bee
 
 ### Stacked Recurrent Neural Network
 
-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\[[2](#Reference)\].
+*Deep Neural Networks* can extract hierarchical representations. The higher layers can form relatively abstract/complex representations, based on primitive features discovered through the lower layers. Unfolding LSTMs through time results in a deep feed-forward neural network. This is because any computational path between the input at time $k < t$ to the output at time $t$ crosses several nonlinear layers. On the other hand, due to parameter sharing over time, LSTMs are also *shallow*; the computation carried out at each time-step is just a linear transformation. Deep LSTM networks 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 efficient at representing some functions and modeling varying-length dependencies\[[2](#Reference)\].
+
 
+However, a deep LSTM network increases the number of nonlinear steps the gradient has to traverse when propagated back in depth. As a result, while LSTMs of 4 layers can be trained properly, those with 4-8 have much worse performance. 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.
 
-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.
 
+A single LSTM cell has three operations:
 
-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.
+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.
+Fig.3 illustrates the final stacked recurrent neural networks.
 
 <p align="center">  
 <img src="./image/stacked_lstm_en.png" width = "40%"  align=center><br>