index_en.html



<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
  <meta charset="utf-8">
  
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  
  <title>Semantic Role labeling Tutorial &mdash; PaddlePaddle  documentation</title>
  

    <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
  

        <link rel="index" title="Index"
              href="../../genindex.html"/>
        <link rel="search" title="Search" href="../../search.html"/>
    <link rel="top" title="PaddlePaddle  documentation" href="../../index.html"/>
        <link rel="up" title="TUTORIALS" href="../index_en.html"/>
        <link rel="next" title="Text generation Tutorial" href="../text_generation/index_en.html"/>
        <link rel="prev" title="Sentiment Analysis Tutorial" href="../sentiment_analysis/index_en.html"/> 

  <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
  <link rel="stylesheet" href="../../_static/css/override.css" type="text/css" />
  <script>
  var _hmt = _hmt || [];
  (function() {
    var hm = document.createElement("script");
    hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
    var s = document.getElementsByTagName("script")[0]; 
    s.parentNode.insertBefore(hm, s);
  })();
  </script>

  
  <script src="../../_static/js/modernizr.min.js"></script>

</head>

<body class="wy-body-for-nav" role="document">

  
  <header class="site-header">
    <div class="site-logo">
      <a href="/"><img src="../../_static/images/PP_w.png"></a>
    </div>
    <div class="site-nav-links">
      <div class="site-menu">
        <a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Folk me on Github</a>
        <div class="language-switcher dropdown">
          <a type="button" data-toggle="dropdown">
            <span>English</span>
            <i class="fa fa-angle-up"></i>
            <i class="fa fa-angle-down"></i>
          </a>
          <ul class="dropdown-menu">
            <li><a href="/doc_cn">中文</a></li>
            <li><a href="/doc">English</a></li>
          </ul>
        </div>
        <ul class="site-page-links">
          <li><a>Home</a></li>
          <li><a>Get Started</a></li>
          <li class="active"><a>Documentation</a></li>
          <li><a>About Us</a></li>
        </ul>
      </div>
      <div class="doc-module">
        
        <ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../index_en.html">TUTORIALS</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
</ul>

        
<div role="search">
  <form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" />
    <input type="hidden" name="check_keywords" value="yes" />
    <input type="hidden" name="area" value="default" />
  </form>
</div>        
      </div>
    </div>
  </header>
  
  <div class="main-content-wrap">

    
    <nav class="doc-menu-vertical" role="navigation">
        
          
          <ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/ubuntu_install_en.html">Debian Package installation guide</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/build_from_source_en.html">Installing from Sources</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../getstarted/basic_usage/index_en.html">Simple Linear Regression</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../index_en.html">TUTORIALS</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../quick_start/index_en.html">Quick Start</a></li>
<li class="toctree-l2"><a class="reference internal" href="../rec/ml_regression_en.html">MovieLens Regression</a></li>
<li class="toctree-l2"><a class="reference internal" href="../image_classification/index_en.html">Image Classification</a></li>
<li class="toctree-l2"><a class="reference internal" href="../sentiment_analysis/index_en.html">Sentiment Analysis</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Semantic Role Labeling</a></li>
<li class="toctree-l2"><a class="reference internal" href="../text_generation/index_en.html">Text Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../gan/index_en.html">Image Auto-Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../imagenet_model/resnet_model_en.html">ImageNet: ResNet</a></li>
<li class="toctree-l2"><a class="reference internal" href="../embedding_model/index_en.html">Embedding: Chinese Word</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cluster/cluster_train_en.html">Run Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Datasets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
</ul>

        
    </nav>
    
    <nav class="local-toc"><ul>
<li><a class="reference internal" href="#">Semantic Role labeling Tutorial</a><ul>
<li><a class="reference internal" href="#data-description">Data Description</a></li>
<li><a class="reference internal" href="#training">Training</a><ul>
<li><a class="reference internal" href="#db-lstm">DB-LSTM</a></li>
<li><a class="reference internal" href="#features">Features</a></li>
<li><a class="reference internal" href="#data-provider">Data Provider</a></li>
<li><a class="reference internal" href="#neural-network-config">Neural Network Config</a></li>
<li><a class="reference internal" href="#run-training">Run Training</a></li>
<li><a class="reference internal" href="#run-testing">Run testing</a></li>
<li><a class="reference internal" href="#run-prediction">Run prediction</a></li>
</ul>
</li>
<li><a class="reference internal" href="#reference">Reference</a></li>
</ul>
</li>
</ul>
</nav>
    
    <section class="doc-content-wrap">

      
<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
      
        <li><a href="../index_en.html">TUTORIALS</a> > </li>
      
    <li>Semantic Role labeling Tutorial</li>
  </ul>
</div>
      
      <div class="wy-nav-content" id="doc-content">
        <div class="rst-content">
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <div class="section" id="semantic-role-labeling-tutorial">
<span id="semantic-role-labeling-tutorial"></span><span id="semantic-role-labeling"></span><h1>Semantic Role labeling Tutorial<a class="headerlink" href="#semantic-role-labeling-tutorial" title="Permalink to this headline">¶</a></h1>
<p>Semantic role labeling (SRL) is a form of shallow semantic parsing whose goal is to discover the predicate-argument structure of each predicate in a given input sentence. SRL is useful as an intermediate step in a wide range of natural language processing tasks, such as information extraction. automatic document categorization and question answering.  An instance is as following [1]:</p>
<p>[ <sub>A0</sub> He ] [ <sub>AM-MOD</sub> would ][ <sub>AM-NEG</sub> n’t ] [ <sub>V</sub> accept] [ <sub>A1</sub> anything of value ] from [<sub>A2</sub> those he was writing about ].</p>
<ul class="simple">
<li>V: verb</li>
<li>A0: acceptor</li>
<li>A1: thing accepted</li>
<li>A2: accepted-from</li>
<li>A3: Attribute</li>
<li>AM-MOD: modal</li>
<li>AM-NEG: negation</li>
</ul>
<p>Given the verb &#8220;accept&#8221;, the chunks in sentence would play certain semantic roles. Here, the label scheme is from Penn Proposition Bank.</p>
<p>To this date, most of the successful SRL systems are built on top of some form of parsing results where pre-defined feature templates over the syntactic structure are used. This tutorial will present an end-to-end system using deep bidirectional long short-term memory (DB-LSTM)[2] for solving the SRL task, which largely outperforms the previous state-of-the-art systems. The system regards SRL task as the sequence labelling problem.</p>
<div class="section" id="data-description">
<span id="data-description"></span><h2>Data Description<a class="headerlink" href="#data-description" title="Permalink to this headline">¶</a></h2>
<p>The relevant paper[2] takes the data set in CoNLL-2005&amp;2012 Shared Task for training and testing. Accordingto data license,  the demo adopts the test data set of CoNLL-2005, which can be reached on website.</p>
<p>To download and process the original data, user just need to execute the following command:</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="nb">cd</span> data
./get_data.sh
</pre></div>
</div>
<p>Several new files appear in the <code class="docutils literal"><span class="pre">data</span></code>directory as follows.</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span>conll05st-release：the <span class="nb">test</span> data <span class="nb">set</span> of CoNll-2005 shared task 
test.wsj.words：the Wall Street Journal data sentences
test.wsj.props:  the propositional arguments
feature: the extracted features from data <span class="nb">set</span>
</pre></div>
</div>
</div>
<div class="section" id="training">
<span id="training"></span><h2>Training<a class="headerlink" href="#training" title="Permalink to this headline">¶</a></h2>
<div class="section" id="db-lstm">
<span id="db-lstm"></span><h3>DB-LSTM<a class="headerlink" href="#db-lstm" title="Permalink to this headline">¶</a></h3>
<p>Please refer to the Sentiment Analysis demo to learn more about the long short-term memory unit.</p>
<p>Unlike Bidirectional-LSTM that used in Sentiment Analysis demo,  the DB-LSTM adopts another way to stack LSTM layer. First a standard LSTM processes the sequence in forward direction. The input and output of this LSTM layer are taken by the next LSTM layer as input, processed in reversed direction. These two standard LSTM layers compose a pair of LSTM. Then we stack LSTM layers pair after pair to obtain the deep LSTM model.</p>
<p>The following figure shows a temporal expanded 2-layer DB-LSTM network.
<center>
<img alt="pic" src="../../_images/network_arch.png" />
</center></p>
</div>
<div class="section" id="features">
<span id="features"></span><h3>Features<a class="headerlink" href="#features" title="Permalink to this headline">¶</a></h3>
<p>Two input features play an essential role in this pipeline: predicate (pred) and argument (argu). Two other features: predicate context (ctx-p) and region mark (mr) are also adopted. Because 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 predicate context, the ambiguity can be largely eliminated. Similarly, we use region mark m<sub>r</sub> = 1 to denote the argument position if it locates in the predicate context region, or m<sub>r</sub> = 0 if does not. These four simple features are all we need for our SRL system. Features of one sample with context size set to 1 is showed as following[2]:
<center>
<img alt="pic" src="../../_images/feature.jpg" />
</center></p>
<p>In this sample, the coresponding labelled sentence is:</p>
<p>[ <sub>A1</sub> A record date ] has [ <sub>AM-NEG</sub> n&#8217;t ] been [ <sub>V</sub> set ] .</p>
<p>In the demo, we adopt the feature template as above, consists of :  <code class="docutils literal"><span class="pre">argument</span></code>, <code class="docutils literal"><span class="pre">predicate</span></code>, <code class="docutils literal"><span class="pre">ctx-p</span> <span class="pre">(p=-1,0,1)</span></code>, <code class="docutils literal"><span class="pre">mark</span></code> and use <code class="docutils literal"><span class="pre">B/I/O</span></code> scheme to label each argument. These features and labels are stored in <code class="docutils literal"><span class="pre">feature</span></code> file, and separated by <code class="docutils literal"><span class="pre">\t</span></code>.</p>
</div>
<div class="section" id="data-provider">
<span id="data-provider"></span><h3>Data Provider<a class="headerlink" href="#data-provider" title="Permalink to this headline">¶</a></h3>
<p><code class="docutils literal"><span class="pre">dataprovider.py</span></code> is the python file to wrap data. <code class="docutils literal"><span class="pre">hook()</span></code> function is to define the data slots for network. The  Six features and label are all IndexSlots.</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">hook</span><span class="p">(</span><span class="n">settings</span><span class="p">,</span> <span class="n">word_dict</span><span class="p">,</span> <span class="n">label_dict</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
    <span class="n">settings</span><span class="o">.</span><span class="n">word_dict</span> <span class="o">=</span> <span class="n">word_dict</span>
    <span class="n">settings</span><span class="o">.</span><span class="n">label_dict</span> <span class="o">=</span> <span class="n">label_dict</span>
    <span class="c1">#all inputs are integral and sequential type</span>
    <span class="n">settings</span><span class="o">.</span><span class="n">slots</span> <span class="o">=</span> <span class="p">[</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">word_dict</span><span class="p">)),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">predicate_dict</span><span class="p">)),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">word_dict</span><span class="p">)),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">word_dict</span><span class="p">)),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">word_dict</span><span class="p">)),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">word_dict</span><span class="p">)),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">word_dict</span><span class="p">)),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="mi">2</span><span class="p">),</span>
        <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">label_dict</span><span class="p">))]</span>
</pre></div>
</div>
<p>The corresponding data iterator is as following:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="nd">@provider</span><span class="p">(</span><span class="n">init_hook</span><span class="o">=</span><span class="n">hook</span><span class="p">,</span> <span class="n">should_shuffle</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">calc_batch_size</span><span class="o">=</span><span class="n">get_batch_size</span><span class="p">,</span>
          <span class="n">can_over_batch_size</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">cache</span><span class="o">=</span><span class="n">CacheType</span><span class="o">.</span><span class="n">CACHE_PASS_IN_MEM</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="n">settings</span><span class="p">,</span> <span class="n">file_name</span><span class="p">):</span>
    <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">file_name</span><span class="p">,</span> <span class="s1">&#39;r&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">fdata</span><span class="p">:</span>
        <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">fdata</span><span class="p">:</span>
            <span class="n">sentence</span><span class="p">,</span> <span class="n">predicate</span><span class="p">,</span> <span class="n">ctx_n2</span><span class="p">,</span> <span class="n">ctx_n1</span><span class="p">,</span> <span class="n">ctx_0</span><span class="p">,</span> <span class="n">ctx_p1</span><span class="p">,</span> <span class="n">ctx_p2</span><span class="p">,</span>  <span class="n">mark</span><span class="p">,</span> <span class="n">label</span> <span class="o">=</span> \
                <span class="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\t</span><span class="s1">&#39;</span><span class="p">)</span>

            <span class="n">words</span> <span class="o">=</span> <span class="n">sentence</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
            <span class="n">sen_len</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">words</span><span class="p">)</span>
            <span class="n">word_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">word_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">w</span><span class="p">,</span> <span class="n">UNK_IDX</span><span class="p">)</span> <span class="k">for</span> <span class="n">w</span> <span class="ow">in</span> <span class="n">words</span><span class="p">]</span>

            <span class="n">predicate_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">predicate_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">predicate</span><span class="p">)]</span> <span class="o">*</span> <span class="n">sen_len</span>
            <span class="n">ctx_n2_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">word_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">ctx_n2</span><span class="p">,</span> <span class="n">UNK_IDX</span><span class="p">)]</span> <span class="o">*</span> <span class="n">sen_len</span>
            <span class="n">ctx_n1_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">word_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">ctx_n1</span><span class="p">,</span> <span class="n">UNK_IDX</span><span class="p">)]</span> <span class="o">*</span> <span class="n">sen_len</span>
            <span class="n">ctx_0_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">word_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">ctx_0</span><span class="p">,</span> <span class="n">UNK_IDX</span><span class="p">)]</span> <span class="o">*</span> <span class="n">sen_len</span>
            <span class="n">ctx_p1_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">word_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">ctx_p1</span><span class="p">,</span> <span class="n">UNK_IDX</span><span class="p">)]</span> <span class="o">*</span> <span class="n">sen_len</span>
            <span class="n">ctx_p2_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">word_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">ctx_p2</span><span class="p">,</span> <span class="n">UNK_IDX</span><span class="p">)]</span> <span class="o">*</span> <span class="n">sen_len</span>

            <span class="n">marks</span> <span class="o">=</span> <span class="n">mark</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
            <span class="n">mark_slot</span> <span class="o">=</span> <span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="n">w</span><span class="p">)</span> <span class="k">for</span> <span class="n">w</span> <span class="ow">in</span> <span class="n">marks</span><span class="p">]</span>

            <span class="n">label_list</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
            <span class="n">label_slot</span> <span class="o">=</span> <span class="p">[</span><span class="n">settings</span><span class="o">.</span><span class="n">label_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">w</span><span class="p">)</span> <span class="k">for</span> <span class="n">w</span> <span class="ow">in</span> <span class="n">label_list</span><span class="p">]</span>
            <span class="k">yield</span> <span class="n">word_slot</span><span class="p">,</span> <span class="n">predicate_slot</span><span class="p">,</span> <span class="n">ctx_n2_slot</span><span class="p">,</span> <span class="n">ctx_n1_slot</span><span class="p">,</span> \
                  <span class="n">ctx_0_slot</span><span class="p">,</span> <span class="n">ctx_p1_slot</span><span class="p">,</span> <span class="n">ctx_p2_slot</span><span class="p">,</span> <span class="n">mark_slot</span><span class="p">,</span> <span class="n">label_slot</span>
</pre></div>
</div>
<p>The <code class="docutils literal"><span class="pre">process</span></code>function yield 9 lists which are 8 features and label.</p>
</div>
<div class="section" id="neural-network-config">
<span id="neural-network-config"></span><h3>Neural Network Config<a class="headerlink" href="#neural-network-config" title="Permalink to this headline">¶</a></h3>
<p><code class="docutils literal"><span class="pre">db_lstm.py</span></code> is the neural network config file to load the dictionaries and define the  data provider module and network architecture during the training procedure.</p>
<p>Nine <code class="docutils literal"><span class="pre">data_layer</span></code> load instances from data provider. Eight features are transformed into embedddings respectively, and mixed by <code class="docutils literal"><span class="pre">mixed_layer</span></code> .  Deep bidirectional LSTM layers extract features for the softmax layer. The objective function is cross entropy of labels.</p>
</div>
<div class="section" id="run-training">
<span id="run-training"></span><h3>Run Training<a class="headerlink" href="#run-training" title="Permalink to this headline">¶</a></h3>
<p>The script for training is <code class="docutils literal"><span class="pre">train.sh</span></code>, user just need to execute:</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span>  ./train.sh
</pre></div>
</div>
<p>The content in <code class="docutils literal"><span class="pre">train.sh</span></code>:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">paddle</span> <span class="n">train</span> \
  <span class="o">--</span><span class="n">config</span><span class="o">=./</span><span class="n">db_lstm</span><span class="o">.</span><span class="n">py</span> \
  <span class="o">--</span><span class="n">use_gpu</span><span class="o">=</span><span class="mi">0</span> \
  <span class="o">--</span><span class="n">log_period</span><span class="o">=</span><span class="mi">5000</span> \
  <span class="o">--</span><span class="n">trainer_count</span><span class="o">=</span><span class="mi">1</span> \
  <span class="o">--</span><span class="n">show_parameter_stats_period</span><span class="o">=</span><span class="mi">5000</span> \
  <span class="o">--</span><span class="n">save_dir</span><span class="o">=./</span><span class="n">output</span> \
  <span class="o">--</span><span class="n">num_passes</span><span class="o">=</span><span class="mi">10000</span> \
  <span class="o">--</span><span class="n">average_test_period</span><span class="o">=</span><span class="mi">10000000</span> \
  <span class="o">--</span><span class="n">init_model_path</span><span class="o">=./</span><span class="n">data</span> \
  <span class="o">--</span><span class="n">load_missing_parameter_strategy</span><span class="o">=</span><span class="n">rand</span> \
  <span class="o">--</span><span class="n">test_all_data_in_one_period</span><span class="o">=</span><span class="mi">1</span> \
<span class="mi">2</span><span class="o">&gt;&amp;</span><span class="mi">1</span> <span class="o">|</span> <span class="n">tee</span> <span class="s1">&#39;train.log&#39;</span>
</pre></div>
</div>
<ul class="simple">
<li>--config=./db_lstm.py : network config file.</li>
<li>--use_gpu=false: use CPU to train, set true, if you install GPU version of PaddlePaddle and want to use GPU to train, until now crf_layer do not support GPU</li>
<li>--log_period=500: print log every 20 batches.</li>
<li>--trainer_count=1: set thread number (or GPU count).</li>
<li>--show_parameter_stats_period=5000: show parameter statistic every 100 batches.</li>
<li>--save_dir=./output: output path to save models.</li>
<li>--num_passes=10000: set pass number, one pass in PaddlePaddle means training all samples in dataset one time.</li>
<li>--average_test_period=10000000:  do test on average parameter every average_test_period batches</li>
<li>--init_model_path=./data: parameter initialization path</li>
<li>--load_missing_parameter_strategy=rand: random initialization unexisted parameters</li>
<li>--test_all_data_in_one_period=1: test all data in one period</li>
</ul>
<p>After training, the models  will be saved in directory <code class="docutils literal"><span class="pre">output</span></code>. Our training curve is as following:
<center>
<img alt="pic" src="../../_images/curve.jpg" />
</center></p>
</div>
<div class="section" id="run-testing">
<span id="run-testing"></span><h3>Run testing<a class="headerlink" href="#run-testing" title="Permalink to this headline">¶</a></h3>
<p>The script for testing is <code class="docutils literal"><span class="pre">test.sh</span></code>, user just need to execute:</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span>  ./test.sh
</pre></div>
</div>
<p>The main part in <code class="docutils literal"><span class="pre">tesh.sh</span></code></p>
<div class="highlight-default"><div class="highlight"><pre><span></span>paddle train \
  --config=./db_lstm.py \
  --model_list=$model_list \
  --job=test \
  --config_args=is_test=1 \
</pre></div>
</div>
<ul class="simple">
<li>--config=./db_lstm.py: network config file</li>
<li>--model_list=$model_list.list: model list file</li>
<li>--job=test: indicate the test job</li>
<li>--config_args=is_test=1: flag to indicate test</li>
<li>--test_all_data_in_one_period=1: test all data in 1 period</li>
</ul>
</div>
<div class="section" id="run-prediction">
<span id="run-prediction"></span><h3>Run prediction<a class="headerlink" href="#run-prediction" title="Permalink to this headline">¶</a></h3>
<p>The script for prediction is <code class="docutils literal"><span class="pre">predict.sh</span></code>, user just need to execute:</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span>  ./predict.sh
  
</pre></div>
</div>
<p>In <code class="docutils literal"><span class="pre">predict.sh</span></code>, user should offer the network config file, model path, label file, word dictionary file, feature file</p>
<div class="highlight-default"><div class="highlight"><pre><span></span>python predict.py 
     -c $config_file \
     -w $best_model_path \
     -l $label_file \
     -p $predicate_dict_file  \
     -d $dict_file \
     -i $input_file \
     -o $output_file
</pre></div>
</div>
<p><code class="docutils literal"><span class="pre">predict.py</span></code> is the main executable python script, which includes functions: load model, load data, data prediction. The network model will output the probability distribution of labels. In the demo, we take the label with maximum probability as result. User can also implement the beam search or viterbi decoding upon the probability distribution matrix.</p>
<p>After prediction,  the result is saved in <code class="docutils literal"><span class="pre">predict.res</span></code>.</p>
</div>
</div>
<div class="section" id="reference">
<span id="reference"></span><h2>Reference<a class="headerlink" href="#reference" title="Permalink to this headline">¶</a></h2>
<p>[1] Martha Palmer, Dan Gildea, and Paul Kingsbury. The Proposition Bank: An Annotated Corpus of Semantic Roles , Computational Linguistics, 31(1), 2005.</p>
<p>[2] Zhou, Jie, and Wei Xu. &#8220;End-to-end learning of semantic role labeling using recurrent neural networks.&#8221; Proceedings of the Annual Meeting of the Association for Computational Linguistics. 2015.</p>
</div>
</div>


           </div>
          </div>
          <footer>
  
    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
      
        <a href="../text_generation/index_en.html" class="btn btn-neutral float-right" title="Text generation Tutorial" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
      
      
        <a href="../sentiment_analysis/index_en.html" class="btn btn-neutral" title="Sentiment Analysis Tutorial" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
      
    </div>
  

  <hr/>

  <div role="contentinfo">
    <p>
        &copy; Copyright 2016, PaddlePaddle developers.

    </p>
  </div>
  Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. 

</footer>

        </div>
      </div>

    </section>

  </div>
  

    <script type="text/javascript">
        var DOCUMENTATION_OPTIONS = {
            URL_ROOT:'../../',
            VERSION:'',
            COLLAPSE_INDEX:false,
            FILE_SUFFIX:'.html',
            HAS_SOURCE:  true
        };
    </script>
      <script type="text/javascript" src="../../_static/jquery.js"></script>
      <script type="text/javascript" src="../../_static/underscore.js"></script>
      <script type="text/javascript" src="../../_static/doctools.js"></script>
      <script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
       
  
    <script type="text/javascript" src="../../_static/js/theme.js"></script>
  
  
  <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
  <script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
  <script src="../../_static/js/paddle_doc_init.js"></script> 

</body>
</html>