http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6/faq.html
----------------------------------------------------------------------
diff --git a/6/faq.html b/6/faq.html
new file mode 100644
index 0000000..8db5143
--- /dev/null
+++ b/6/faq.html
@@ -0,0 +1,376 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="description" content="">
+    <meta name="author" content="">
+    <link rel="icon" href="../../favicon.ico">
+
+    <title>Joshua Documentation | Frequently Asked Questions</title>
+
+    <!-- Bootstrap core CSS -->
+    <link href="/dist/css/bootstrap.min.css" rel="stylesheet">
+
+    <!-- Custom styles for this template -->
+    <link href="/joshua6.css" rel="stylesheet">
+  </head>
+
+  <body>
+
+    <div class="blog-masthead">
+      <div class="container">
+        <nav class="blog-nav">
+          <!-- <a class="blog-nav-item active" href="#">Joshua</a> -->
+          <a class="blog-nav-item" href="/">Joshua</a>
+          <!-- <a class="blog-nav-item" href="/6.0/whats-new.html">New 
features</a> -->
+          <a class="blog-nav-item" href="/language-packs/">Language packs</a>
+          <a class="blog-nav-item" href="/data/">Datasets</a>
+          <a class="blog-nav-item" href="/support/">Support</a>
+          <a class="blog-nav-item" href="/contributors.html">Contributors</a>
+        </nav>
+      </div>
+    </div>
+
+    <div class="container">
+
+      <div class="row">
+
+        <div class="col-sm-2">
+          <div class="sidebar-module">
+            <!-- <h4>About</h4> -->
+            <center>
+            <img src="/images/joshua-logo-small.png" />
+            <p>Joshua machine translation toolkit</p>
+            </center>
+          </div>
+          <hr>
+          <center>
+            <a href="/releases/current/" target="_blank"><button 
class="button">Download Joshua 6.0.5</button></a>
+            <br />
+            <a href="/releases/runtime/" target="_blank"><button 
class="button">Runtime only version</button></a>
+            <p>Released November 5, 2015</p>
+          </center>
+          <hr>
+          <!-- <div class="sidebar-module"> -->
+          <!--   <span id="download"> -->
+          <!--     <a 
href="http://joshua-decoder.org/downloads/joshua-6.0.tgz";>Download</a> -->
+          <!--   </span> -->
+          <!-- </div> -->
+          <div class="sidebar-module">
+            <h4>Using Joshua</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/install.html">Installation</a></li>
+              <li><a href="/6.0/quick-start.html">Quick Start</a></li>
+            </ol>
+          </div>
+          <hr>
+          <div class="sidebar-module">
+            <h4>Building new models</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/pipeline.html">Pipeline</a></li>
+              <li><a href="/6.0/tutorial.html">Tutorial</a></li>
+              <li><a href="/6.0/faq.html">FAQ</a></li>
+            </ol>
+          </div>
+<!--
+          <div class="sidebar-module">
+            <h4>Phrase-based</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/phrase.html">Training</a></li>
+            </ol>
+          </div>
+-->
+          <hr>
+          <div class="sidebar-module">
+            <h4>Advanced</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/bundle.html">Building language packs</a></li>
+              <li><a href="/6.0/decoder.html">Decoder options</a></li>
+              <li><a href="/6.0/file-formats.html">File formats</a></li>
+              <li><a href="/6.0/packing.html">Packing TMs</a></li>
+              <li><a href="/6.0/large-lms.html">Building large LMs</a></li>
+            </ol>
+          </div>
+
+          <hr> 
+          <div class="sidebar-module">
+            <h4>Developer</h4>
+            <ol class="list-unstyled">              
+               <li><a 
href="https://github.com/joshua-decoder/joshua";>Github</a></li>
+               <li><a 
href="http://cs.jhu.edu/~post/joshua-docs";>Javadoc</a></li>
+               <li><a 
href="https://groups.google.com/forum/?fromgroups#!forum/joshua_developers";>Mailing
 list</a></li>              
+            </ol>
+          </div>
+
+        </div><!-- /.blog-sidebar -->
+
+        
+        <div class="col-sm-8 blog-main">
+        
+
+          <div class="blog-title">
+            <h2>Frequently Asked Questions</h2>
+          </div>
+          
+          <div class="blog-post">
+
+            <p>Solutions to common problems will be posted here as we become 
aware of
+them.  If you need help with something, please check
+<a href="https://groups.google.com/forum/#!forum/joshua_support";>our support 
group</a>
+for a solution, or
+<a href="https://groups.google.com/forum/#!newtopic/joshua_support";>post a new 
question</a>.</p>
+
+<h3 id="i-get-a-message-stating-no-ken-in-javalibrarypath">I get a message 
stating: “no ken in java.library.path”</h3>
+
+<p>This occurs when <a href="https://kheafield.com/code/kenlm/";>KenLM</a> 
failed to
+build. This can occur for a number of reasons:</p>
+
+<ul>
+  <li>
+    <p><a href="http://www.boost.org/";>Boost</a> isn’t installed. Boost is
+available through most package management tools, so try that
+first. You can also build it from source.</p>
+  </li>
+  <li>
+    <p>Boost is installed, but not in your path. The easiest solution is
+to add the boost library directory to your <code 
class="highlighter-rouge">$LD_LIBRARY_PATH</code>
+environment variable. You can also edit the file
+<code 
class="highlighter-rouge">$JOSHUA/src/joshua/decoder/ff/lm/kenlm/Makefile</code>
 and define
+<code class="highlighter-rouge">BOOST_ROOT</code> to point to your boost 
location. Then rebuild KenLM
+with the command</p>
+
+    <div class="highlighter-rouge"><pre class="highlight"><code>ant -f 
$JOSHUA/build.xml kenlm
+</code></pre>
+    </div>
+  </li>
+  <li>
+    <p>You have run into boost’s weird naming of multi-threaded
+libraries. For some reason, boost libraries sometimes have a
+<code class="highlighter-rouge">-mt</code> extension applied when they are 
built with multi-threaded
+support. This will cause the linker to fail, since it is looking
+for, e.g., <code class="highlighter-rouge">-lboost_system</code> instead of 
<code class="highlighter-rouge">-lboost_system-mt</code>. Edit
+the same Makefile as above and uncomment the <code 
class="highlighter-rouge">BOOST_MT = -mt</code>
+line, then try to compile again with</p>
+
+    <div class="highlighter-rouge"><pre class="highlight"><code>ant -f 
$JOSHUA.build.xml kenlm
+</code></pre>
+    </div>
+  </li>
+</ul>
+
+<p>You may find the following reference URLs to be useful.</p>
+
+<div class="highlighter-rouge"><pre 
class="highlight"><code>https://groups.google.com/forum/#!topic/joshua_support/SiGO41tkpsw
+http://stackoverflow.com/questions/12583080/c-library-in-using-boost-library
+</code></pre>
+</div>
+
+<h3 id="how-do-i-make-joshua-produce-better-results">How do I make Joshua 
produce better results?</h3>
+
+<p>One way is to add a larger language model. Build on Gigaword, news
+crawl data, etc. <code class="highlighter-rouge">lmplz</code> makes it easy to 
build and efficient to
+represent (especially if you compress it with `build_binary). To
+include it in Joshua, there are two ways:</p>
+
+<ul>
+  <li>
+    <p><em>Pipeline</em>. By default, Joshua’s pipeline builds a language
+ model on the target side of your parallel training data. But
+ Joshua can decode with any number of additional language models
+ as well. So you can build a language model separately,
+ presumably on much more data (since you won’t be constrained
+ only to one side of parallel data, which is much more scarce
+ than monolingual data). Once you’ve built extra language models
+ and compiled them with KenLM’s <code 
class="highlighter-rouge">build_binary</code> script, you can
+ tell the pipeline to use them with any number of <code 
class="highlighter-rouge">--lmfile
+ /path/to/lm/file</code> flags.</p>
+  </li>
+  <li>
+    <p><em>Joshua</em> (directly).
+    <a href="http://localhost:4000/6.0/file-formats.html";>This file</a>
+    documents the Joshua configuration file format.</p>
+  </li>
+</ul>
+
+<h3 
id="i-have-already-run-the-pipeline-once-how-do-i-run-it-again-skipping-the-early-stages-and-just-retuning-the-model">I
 have already run the pipeline once. How do I run it again, skipping the early 
stages and just retuning the model?</h3>
+
+<p>You would need to do this if, for example, you added a language
+model, or changed some other parameter (e.g., an improvement to the
+decoder). To do this, follow the following steps:</p>
+
+<ul>
+  <li>Re-run the pipeline giving it a new <code 
class="highlighter-rouge">--rundir N+1</code> (where <code 
class="highlighter-rouge">N</code> is the last
+run, and <code class="highlighter-rouge">N+1</code> is a new, non-existent 
directory). </li>
+  <li>Give it all the other flags that you gave before, such as the
+tuning data, testing data, source and target flags, etc. You
+don’t have to give it the training data.</li>
+  <li>Tell it to start at the tuning step with <code 
class="highlighter-rouge">--first-step TUNE</code></li>
+  <li>Tell it where all of your language model files are with <code 
class="highlighter-rouge">--lmfile
+/path/to/lm</code> lines. You also have to tell it where the main
+language model is, which is usually <code class="highlighter-rouge">--lmfile 
N/lm.kenlm</code> (paths
+are relative to the directory above the run directory.</li>
+  <li>Tell it where the main grammar is, e.g., <code 
class="highlighter-rouge">--grammar
+N/grammar.gz</code>. If the tuning and test data hasn’t changed, you
+can also point it to the filtered and packed versions to save a
+little time using <code class="highlighter-rouge">--tune-grammar 
N/data/tune/grammar.packed</code> and
+<code class="highlighter-rouge">--test-grammar 
N/data/test/grammar.packed</code>, where <code 
class="highlighter-rouge">N</code> here again
+is the previous run (or some other run; it can be anywhere).</li>
+</ul>
+
+<p>Here’s an example. Let’s say you ran a full pipeline as run 1, and
+now added a new language model and want to see how it affects the
+decoder. Your first run might have been invoked like this:</p>
+
+<div class="highlighter-rouge"><pre 
class="highlight"><code>$JOSHUA/scripts/training/pipeline.pl \
+  --rundir 1 \
+  --readme "Baseline French--English Europarl hiero system" \
+  --corpus /path/to/europarl \
+  --tune /path/to/europarl/tune \
+  --test /path/to/europarl/test \
+  --source fr \
+  --target en \
+  --threads 8 \
+  --joshua-mem 30g \
+  --tuner mira \
+  --type hiero \
+  --aligner berkeley
+</code></pre>
+</div>
+
+<p>Your new run will look like this:</p>
+
+<div class="highlighter-rouge"><pre 
class="highlight"><code>$JOSHUA/scripts/training/pipeline.pl \
+  --rundir 2 \
+  --readme "Adding in a huge language model" \
+  --tune /path/to/europarl/tune \
+  --test /path/to/europarl/test \
+  --source fr \
+  --target en \
+  --threads 8 \
+  --joshua-mem 30g \
+  --tuner mira \
+  --type hiero \
+  --aligner berkeley \
+  --first-step TUNE \
+  --lmfile 1/lm.kenlm \
+  --lmfile /path/to/huge/new/lm \
+  --tune-grammar 1/data/tune/grammar.packed \
+  --test-grammar 1/data/test/grammar.packed
+</code></pre>
+</div>
+
+<p>Notice the changes: we removed the <code 
class="highlighter-rouge">--corpus</code> (though it would have
+been fine to have left it, it would have just been skipped),
+specified the first step, changed the run directory and README
+comments, and pointed to the grammars and <em>both</em> language model 
files.</p>
+
+<p>How can I enable specific feature functions?</p>
+
+<p>Let’s say you created a new feature function, <code 
class="highlighter-rouge">OracleFeature</code>, and
+you want to enable it. You can do this in two ways. Through the
+pipeline, simply pass it the argument <code 
class="highlighter-rouge">--joshua-args "list of
+joshua args"</code>. These will then be passed to the decoder when it is
+invoked. You can enable your feature functions, then using
+something like</p>
+
+<div class="highlighter-rouge"><pre 
class="highlight"><code>$JOSHUA/bin/pipeline.pl --joshua-args 
'-feature-function OracleFeature'   
+</code></pre>
+</div>
+
+<p>If you call the decoder directly, you can just put that line in
+the configuration file, e.g.,</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>feature-function = 
OracleFeature
+</code></pre>
+</div>
+
+<p>or you can pass it directly to Joshua on the command line using
+the standard notation, e.g.,</p>
+
+<div class="highlighter-rouge"><pre 
class="highlight"><code>$JOSHUA/bin/joshua-decoder -feature-function 
OracleFeature
+</code></pre>
+</div>
+
+<p>These could be stacked, e.g.,</p>
+
+<div class="highlighter-rouge"><pre 
class="highlight"><code>$JOSHUA/bin/joshua-decoder -feature-function 
OracleFeature \
+    -feature-function MagicFeature \
+    -feature-function MTSolverFeature \
+    ...
+</code></pre>
+</div>
+
+
+          <!--   <h4 class="blog-post-title">Welcome to Joshua!</h4> -->
+
+          <!--   <p>This blog post shows a few different types of content 
that's supported and styled with Bootstrap. Basic typography, images, and code 
are all supported.</p> -->
+          <!--   <hr> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis <a href="#">dis 
parturient montes</a>, nascetur ridiculus mus. Aenean eu leo quam. Pellentesque 
ornare sem lacinia quam venenatis vestibulum. Sed posuere consectetur est at 
lobortis. Cras mattis consectetur purus sit amet fermentum.</p> -->
+          <!--   <blockquote> -->
+          <!--     <p>Curabitur blandit tempus porttitor. <strong>Nullam quis 
risus eget urna mollis</strong> ornare vel eu leo. Nullam id dolor id nibh 
ultricies vehicula ut id elit.</p> -->
+          <!--   </blockquote> -->
+          <!--   <p>Etiam porta <em>sem malesuada magna</em> mollis euismod. 
Cras mattis consectetur purus sit amet fermentum. Aenean lacinia bibendum nulla 
sed consectetur.</p> -->
+          <!--   <h2>Heading</h2> -->
+          <!--   <p>Vivamus sagittis lacus vel augue laoreet rutrum faucibus 
dolor auctor. Duis mollis, est non commodo luctus, nisi erat porttitor ligula, 
eget lacinia odio sem nec elit. Morbi leo risus, porta ac consectetur ac, 
vestibulum at eros.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</p> -->
+          <!--   <pre><code>Example code block</code></pre> -->
+          <!--   <p>Aenean lacinia bibendum nulla sed consectetur. Etiam porta 
sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus commodo, 
tortor mauris condimentum nibh, ut fermentum massa.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus. Aenean lacinia bibendum nulla sed consectetur. 
Etiam porta sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus 
commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet 
risus.</p> -->
+          <!--   <ul> -->
+          <!--     <li>Praesent commodo cursus magna, vel scelerisque nisl 
consectetur et.</li> -->
+          <!--     <li>Donec id elit non mi porta gravida at eget metus.</li> 
-->
+          <!--     <li>Nulla vitae elit libero, a pharetra augue.</li> -->
+          <!--   </ul> -->
+          <!--   <p>Donec ullamcorper nulla non metus auctor fringilla. Nulla 
vitae elit libero, a pharetra augue.</p> -->
+          <!--   <ol> -->
+          <!--     <li>Vestibulum id ligula porta felis euismod semper.</li> 
-->
+          <!--     <li>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</li> -->
+          <!--     <li>Maecenas sed diam eget risus varius blandit sit amet 
non magna.</li> -->
+          <!--   </ol> -->
+          <!--   <p>Cras mattis consectetur purus sit amet fermentum. Sed 
posuere consectetur est at lobortis.</p> -->
+          <!-- </div><\!-- /.blog-post -\-> -->
+
+        </div>
+
+      </div><!-- /.row -->
+
+      
+        
+    </div><!-- /.container -->
+
+    <!-- Bootstrap core JavaScript
+    ================================================== -->
+    <!-- Placed at the end of the document so the pages load faster -->
+    <script 
src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js";></script>
+    <script src="../../dist/js/bootstrap.min.js"></script>
+    <!-- <script src="../../assets/js/docs.min.js"></script> -->
+    <!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
+    <!-- <script 
src="../../assets/js/ie10-viewport-bug-workaround.js"></script>
+    -->
+
+    <!-- Start of StatCounter Code for Default Guide -->
+    <script type="text/javascript">
+      var sc_project=8264132; 
+      var sc_invisible=1; 
+      var sc_security="4b97fe2d"; 
+    </script>
+    <script type="text/javascript" 
src="http://www.statcounter.com/counter/counter.js";></script>
+    <noscript>
+      <div class="statcounter">
+        <a title="hit counter joomla" 
+           href="http://statcounter.com/joomla/";
+           target="_blank">
+          <img class="statcounter"
+               src="http://c.statcounter.com/8264132/0/4b97fe2d/1/";
+               alt="hit counter joomla" />
+        </a>
+      </div>
+    </noscript>
+    <!-- End of StatCounter Code for Default Guide -->
+  </body>
+</html>
+

http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6/features.html
----------------------------------------------------------------------
diff --git a/6/features.html b/6/features.html
new file mode 100644
index 0000000..6e617cf
--- /dev/null
+++ b/6/features.html
@@ -0,0 +1,192 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="description" content="">
+    <meta name="author" content="">
+    <link rel="icon" href="../../favicon.ico">
+
+    <title>Joshua Documentation | Features</title>
+
+    <!-- Bootstrap core CSS -->
+    <link href="/dist/css/bootstrap.min.css" rel="stylesheet">
+
+    <!-- Custom styles for this template -->
+    <link href="/joshua6.css" rel="stylesheet">
+  </head>
+
+  <body>
+
+    <div class="blog-masthead">
+      <div class="container">
+        <nav class="blog-nav">
+          <!-- <a class="blog-nav-item active" href="#">Joshua</a> -->
+          <a class="blog-nav-item" href="/">Joshua</a>
+          <!-- <a class="blog-nav-item" href="/6.0/whats-new.html">New 
features</a> -->
+          <a class="blog-nav-item" href="/language-packs/">Language packs</a>
+          <a class="blog-nav-item" href="/data/">Datasets</a>
+          <a class="blog-nav-item" href="/support/">Support</a>
+          <a class="blog-nav-item" href="/contributors.html">Contributors</a>
+        </nav>
+      </div>
+    </div>
+
+    <div class="container">
+
+      <div class="row">
+
+        <div class="col-sm-2">
+          <div class="sidebar-module">
+            <!-- <h4>About</h4> -->
+            <center>
+            <img src="/images/joshua-logo-small.png" />
+            <p>Joshua machine translation toolkit</p>
+            </center>
+          </div>
+          <hr>
+          <center>
+            <a href="/releases/current/" target="_blank"><button 
class="button">Download Joshua 6.0.5</button></a>
+            <br />
+            <a href="/releases/runtime/" target="_blank"><button 
class="button">Runtime only version</button></a>
+            <p>Released November 5, 2015</p>
+          </center>
+          <hr>
+          <!-- <div class="sidebar-module"> -->
+          <!--   <span id="download"> -->
+          <!--     <a 
href="http://joshua-decoder.org/downloads/joshua-6.0.tgz";>Download</a> -->
+          <!--   </span> -->
+          <!-- </div> -->
+          <div class="sidebar-module">
+            <h4>Using Joshua</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/install.html">Installation</a></li>
+              <li><a href="/6.0/quick-start.html">Quick Start</a></li>
+            </ol>
+          </div>
+          <hr>
+          <div class="sidebar-module">
+            <h4>Building new models</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/pipeline.html">Pipeline</a></li>
+              <li><a href="/6.0/tutorial.html">Tutorial</a></li>
+              <li><a href="/6.0/faq.html">FAQ</a></li>
+            </ol>
+          </div>
+<!--
+          <div class="sidebar-module">
+            <h4>Phrase-based</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/phrase.html">Training</a></li>
+            </ol>
+          </div>
+-->
+          <hr>
+          <div class="sidebar-module">
+            <h4>Advanced</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/bundle.html">Building language packs</a></li>
+              <li><a href="/6.0/decoder.html">Decoder options</a></li>
+              <li><a href="/6.0/file-formats.html">File formats</a></li>
+              <li><a href="/6.0/packing.html">Packing TMs</a></li>
+              <li><a href="/6.0/large-lms.html">Building large LMs</a></li>
+            </ol>
+          </div>
+
+          <hr> 
+          <div class="sidebar-module">
+            <h4>Developer</h4>
+            <ol class="list-unstyled">              
+               <li><a 
href="https://github.com/joshua-decoder/joshua";>Github</a></li>
+               <li><a 
href="http://cs.jhu.edu/~post/joshua-docs";>Javadoc</a></li>
+               <li><a 
href="https://groups.google.com/forum/?fromgroups#!forum/joshua_developers";>Mailing
 list</a></li>              
+            </ol>
+          </div>
+
+        </div><!-- /.blog-sidebar -->
+
+        
+        <div class="col-sm-8 blog-main">
+        
+
+          <div class="blog-title">
+            <h2>Features</h2>
+          </div>
+          
+          <div class="blog-post">
+
+            <p>Joshua 5.0 uses a sparse feature representation to encode 
features internally.</p>
+
+
+          <!--   <h4 class="blog-post-title">Welcome to Joshua!</h4> -->
+
+          <!--   <p>This blog post shows a few different types of content 
that's supported and styled with Bootstrap. Basic typography, images, and code 
are all supported.</p> -->
+          <!--   <hr> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis <a href="#">dis 
parturient montes</a>, nascetur ridiculus mus. Aenean eu leo quam. Pellentesque 
ornare sem lacinia quam venenatis vestibulum. Sed posuere consectetur est at 
lobortis. Cras mattis consectetur purus sit amet fermentum.</p> -->
+          <!--   <blockquote> -->
+          <!--     <p>Curabitur blandit tempus porttitor. <strong>Nullam quis 
risus eget urna mollis</strong> ornare vel eu leo. Nullam id dolor id nibh 
ultricies vehicula ut id elit.</p> -->
+          <!--   </blockquote> -->
+          <!--   <p>Etiam porta <em>sem malesuada magna</em> mollis euismod. 
Cras mattis consectetur purus sit amet fermentum. Aenean lacinia bibendum nulla 
sed consectetur.</p> -->
+          <!--   <h2>Heading</h2> -->
+          <!--   <p>Vivamus sagittis lacus vel augue laoreet rutrum faucibus 
dolor auctor. Duis mollis, est non commodo luctus, nisi erat porttitor ligula, 
eget lacinia odio sem nec elit. Morbi leo risus, porta ac consectetur ac, 
vestibulum at eros.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</p> -->
+          <!--   <pre><code>Example code block</code></pre> -->
+          <!--   <p>Aenean lacinia bibendum nulla sed consectetur. Etiam porta 
sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus commodo, 
tortor mauris condimentum nibh, ut fermentum massa.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus. Aenean lacinia bibendum nulla sed consectetur. 
Etiam porta sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus 
commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet 
risus.</p> -->
+          <!--   <ul> -->
+          <!--     <li>Praesent commodo cursus magna, vel scelerisque nisl 
consectetur et.</li> -->
+          <!--     <li>Donec id elit non mi porta gravida at eget metus.</li> 
-->
+          <!--     <li>Nulla vitae elit libero, a pharetra augue.</li> -->
+          <!--   </ul> -->
+          <!--   <p>Donec ullamcorper nulla non metus auctor fringilla. Nulla 
vitae elit libero, a pharetra augue.</p> -->
+          <!--   <ol> -->
+          <!--     <li>Vestibulum id ligula porta felis euismod semper.</li> 
-->
+          <!--     <li>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</li> -->
+          <!--     <li>Maecenas sed diam eget risus varius blandit sit amet 
non magna.</li> -->
+          <!--   </ol> -->
+          <!--   <p>Cras mattis consectetur purus sit amet fermentum. Sed 
posuere consectetur est at lobortis.</p> -->
+          <!-- </div><\!-- /.blog-post -\-> -->
+
+        </div>
+
+      </div><!-- /.row -->
+
+      
+        
+    </div><!-- /.container -->
+
+    <!-- Bootstrap core JavaScript
+    ================================================== -->
+    <!-- Placed at the end of the document so the pages load faster -->
+    <script 
src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js";></script>
+    <script src="../../dist/js/bootstrap.min.js"></script>
+    <!-- <script src="../../assets/js/docs.min.js"></script> -->
+    <!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
+    <!-- <script 
src="../../assets/js/ie10-viewport-bug-workaround.js"></script>
+    -->
+
+    <!-- Start of StatCounter Code for Default Guide -->
+    <script type="text/javascript">
+      var sc_project=8264132; 
+      var sc_invisible=1; 
+      var sc_security="4b97fe2d"; 
+    </script>
+    <script type="text/javascript" 
src="http://www.statcounter.com/counter/counter.js";></script>
+    <noscript>
+      <div class="statcounter">
+        <a title="hit counter joomla" 
+           href="http://statcounter.com/joomla/";
+           target="_blank">
+          <img class="statcounter"
+               src="http://c.statcounter.com/8264132/0/4b97fe2d/1/";
+               alt="hit counter joomla" />
+        </a>
+      </div>
+    </noscript>
+    <!-- End of StatCounter Code for Default Guide -->
+  </body>
+</html>
+

http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6/file-formats.html
----------------------------------------------------------------------
diff --git a/6/file-formats.html b/6/file-formats.html
new file mode 100644
index 0000000..4918253
--- /dev/null
+++ b/6/file-formats.html
@@ -0,0 +1,270 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="description" content="">
+    <meta name="author" content="">
+    <link rel="icon" href="../../favicon.ico">
+
+    <title>Joshua Documentation | Joshua file formats</title>
+
+    <!-- Bootstrap core CSS -->
+    <link href="/dist/css/bootstrap.min.css" rel="stylesheet">
+
+    <!-- Custom styles for this template -->
+    <link href="/joshua6.css" rel="stylesheet">
+  </head>
+
+  <body>
+
+    <div class="blog-masthead">
+      <div class="container">
+        <nav class="blog-nav">
+          <!-- <a class="blog-nav-item active" href="#">Joshua</a> -->
+          <a class="blog-nav-item" href="/">Joshua</a>
+          <!-- <a class="blog-nav-item" href="/6.0/whats-new.html">New 
features</a> -->
+          <a class="blog-nav-item" href="/language-packs/">Language packs</a>
+          <a class="blog-nav-item" href="/data/">Datasets</a>
+          <a class="blog-nav-item" href="/support/">Support</a>
+          <a class="blog-nav-item" href="/contributors.html">Contributors</a>
+        </nav>
+      </div>
+    </div>
+
+    <div class="container">
+
+      <div class="row">
+
+        <div class="col-sm-2">
+          <div class="sidebar-module">
+            <!-- <h4>About</h4> -->
+            <center>
+            <img src="/images/joshua-logo-small.png" />
+            <p>Joshua machine translation toolkit</p>
+            </center>
+          </div>
+          <hr>
+          <center>
+            <a href="/releases/current/" target="_blank"><button 
class="button">Download Joshua 6.0.5</button></a>
+            <br />
+            <a href="/releases/runtime/" target="_blank"><button 
class="button">Runtime only version</button></a>
+            <p>Released November 5, 2015</p>
+          </center>
+          <hr>
+          <!-- <div class="sidebar-module"> -->
+          <!--   <span id="download"> -->
+          <!--     <a 
href="http://joshua-decoder.org/downloads/joshua-6.0.tgz";>Download</a> -->
+          <!--   </span> -->
+          <!-- </div> -->
+          <div class="sidebar-module">
+            <h4>Using Joshua</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/install.html">Installation</a></li>
+              <li><a href="/6.0/quick-start.html">Quick Start</a></li>
+            </ol>
+          </div>
+          <hr>
+          <div class="sidebar-module">
+            <h4>Building new models</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/pipeline.html">Pipeline</a></li>
+              <li><a href="/6.0/tutorial.html">Tutorial</a></li>
+              <li><a href="/6.0/faq.html">FAQ</a></li>
+            </ol>
+          </div>
+<!--
+          <div class="sidebar-module">
+            <h4>Phrase-based</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/phrase.html">Training</a></li>
+            </ol>
+          </div>
+-->
+          <hr>
+          <div class="sidebar-module">
+            <h4>Advanced</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/bundle.html">Building language packs</a></li>
+              <li><a href="/6.0/decoder.html">Decoder options</a></li>
+              <li><a href="/6.0/file-formats.html">File formats</a></li>
+              <li><a href="/6.0/packing.html">Packing TMs</a></li>
+              <li><a href="/6.0/large-lms.html">Building large LMs</a></li>
+            </ol>
+          </div>
+
+          <hr> 
+          <div class="sidebar-module">
+            <h4>Developer</h4>
+            <ol class="list-unstyled">              
+               <li><a 
href="https://github.com/joshua-decoder/joshua";>Github</a></li>
+               <li><a 
href="http://cs.jhu.edu/~post/joshua-docs";>Javadoc</a></li>
+               <li><a 
href="https://groups.google.com/forum/?fromgroups#!forum/joshua_developers";>Mailing
 list</a></li>              
+            </ol>
+          </div>
+
+        </div><!-- /.blog-sidebar -->
+
+        
+        <div class="col-sm-8 blog-main">
+        
+
+          <div class="blog-title">
+            <h2>Joshua file formats</h2>
+          </div>
+          
+          <div class="blog-post">
+
+            <p>This page describes the formats of Joshua configuration and 
support files.</p>
+
+<h2 id="translation-models-grammars">Translation models (grammars)</h2>
+
+<p>Joshua supports two grammar file formats: a text-based version (also used 
by Hiero, shared by
+<a href="">cdec</a>, and supported by <a href="">hierarchical Moses</a>), and 
an efficient
+<a href="packing.html">packed representation</a> developed by <a 
href="http://cs.jhu.edu/~juri";>Juri Ganitkevich</a>.</p>
+
+<p>Grammar rules follow this format.</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>[LHS] ||| 
SOURCE-SIDE ||| TARGET-SIDE ||| FEATURES
+</code></pre>
+</div>
+
+<p>The source and target sides contain a mixture of terminals and 
nonterminals. The nonterminals are
+linked across sides by indices. There is no limit to the number of paired 
nonterminals in the rule
+or on the nonterminal labels (Joshua supports decoding with SAMT and GHKM 
grammars).</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>[X] ||| el chico 
[X,1] ||| the boy [X,1] ||| -3.14 0 2 17
+[S] ||| el chico [VP,1] ||| the boy [VP,1] ||| -3.14 0 2 17
+[VP] ||| [NP,1] [IN,2] [VB,3] ||| [VB,3] [IN,2] [NP,1] ||| 0.0019026637 
0.81322956
+</code></pre>
+</div>
+
+<p>The feature values can have optional labels, e.g.:</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>[X] ||| el chico 
[X,1] ||| the boy [X,1] ||| lexprob=-3.14 lexicalized=1 numwords=2 count=17
+</code></pre>
+</div>
+
+<p>One file common to decoding is the glue grammar, which for hiero grammar is 
defined as follows:</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>[GOAL] ||| 
&lt;s&gt; ||| &lt;s&gt; ||| 0
+[GOAL] ||| [GOAL,1] [X,2] ||| [GOAL,1] [X,2] ||| -1
+[GOAL] ||| [GOAL,1] &lt;/s&gt; ||| [GOAL,1] &lt;/s&gt; ||| 0
+</code></pre>
+</div>
+
+<p>Joshua’s <a href="pipeline.html">pipeline</a> supports extraction of 
Hiero and SAMT grammars via
+<a href="thrax.html">Thrax</a> or GHKM grammars using <a 
href="http://www-nlp.stanford.edu/~mgalley/";>Michel Galley</a>’s
+GHKM extractor (included) or Moses’ GHKM extractor (if Moses is 
installed).</p>
+
+<h2 id="language-model">Language Model</h2>
+
+<p>Joshua has two language model implementations: <a 
href="http://kheafield.com/code/kenlm/";>KenLM</a> and
+<a href="http://berkeleylm.googlecode.com";>BerkeleyLM</a>.  All language model 
implementations support the
+standard ARPA format output by <a 
href="http://www.speech.sri.com/projects/srilm/";>SRILM</a>.  In addition,
+KenLM and BerkeleyLM support compiled formats that can be loaded more quickly 
and efficiently. KenLM
+is written in C++ and is supported via a JNI bridge, while BerkeleyLM is 
written in Java. KenLM is
+the default because of its support for left-state minimization.</p>
+
+<h3 id="compiling-for-kenlm">Compiling for KenLM</h3>
+
+<p>To compile an ARPA grammar for KenLM, use the (provided) <code 
class="highlighter-rouge">build-binary</code> command, located deep within
+the Joshua source code:</p>
+
+<div class="highlighter-rouge"><pre 
class="highlight"><code>$JOSHUA/bin/build_binary lm.arpa lm.kenlm
+</code></pre>
+</div>
+
+<p>This script takes the <code class="highlighter-rouge">lm.arpa</code> file 
and produces the compiled version in <code 
class="highlighter-rouge">lm.kenlm</code>.</p>
+
+<h3 id="compiling-for-berkeleylm">Compiling for BerkeleyLM</h3>
+
+<p>To compile a grammar for BerkeleyLM, type:</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>java -cp 
$JOSHUA/lib/berkeleylm.jar -server -mxMEM 
edu.berkeley.nlp.lm.io.MakeLmBinaryFromArpa lm.arpa lm.berkeleylm
+</code></pre>
+</div>
+
+<p>The <code class="highlighter-rouge">lm.berkeleylm</code> file can then be 
listed directly in the <a href="decoder.html">Joshua configuration file</a>.</p>
+
+<h2 id="joshua-configuration-file">Joshua configuration file</h2>
+
+<p>The <a href="decoder.html">decoder page</a> documents decoder command-line 
and config file options.</p>
+
+<h2 id="thrax-configuration">Thrax configuration</h2>
+
+<p>See <a href="thrax.html">the thrax page</a> for more information about the 
Thrax configuration file.</p>
+
+
+          <!--   <h4 class="blog-post-title">Welcome to Joshua!</h4> -->
+
+          <!--   <p>This blog post shows a few different types of content 
that's supported and styled with Bootstrap. Basic typography, images, and code 
are all supported.</p> -->
+          <!--   <hr> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis <a href="#">dis 
parturient montes</a>, nascetur ridiculus mus. Aenean eu leo quam. Pellentesque 
ornare sem lacinia quam venenatis vestibulum. Sed posuere consectetur est at 
lobortis. Cras mattis consectetur purus sit amet fermentum.</p> -->
+          <!--   <blockquote> -->
+          <!--     <p>Curabitur blandit tempus porttitor. <strong>Nullam quis 
risus eget urna mollis</strong> ornare vel eu leo. Nullam id dolor id nibh 
ultricies vehicula ut id elit.</p> -->
+          <!--   </blockquote> -->
+          <!--   <p>Etiam porta <em>sem malesuada magna</em> mollis euismod. 
Cras mattis consectetur purus sit amet fermentum. Aenean lacinia bibendum nulla 
sed consectetur.</p> -->
+          <!--   <h2>Heading</h2> -->
+          <!--   <p>Vivamus sagittis lacus vel augue laoreet rutrum faucibus 
dolor auctor. Duis mollis, est non commodo luctus, nisi erat porttitor ligula, 
eget lacinia odio sem nec elit. Morbi leo risus, porta ac consectetur ac, 
vestibulum at eros.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</p> -->
+          <!--   <pre><code>Example code block</code></pre> -->
+          <!--   <p>Aenean lacinia bibendum nulla sed consectetur. Etiam porta 
sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus commodo, 
tortor mauris condimentum nibh, ut fermentum massa.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus. Aenean lacinia bibendum nulla sed consectetur. 
Etiam porta sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus 
commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet 
risus.</p> -->
+          <!--   <ul> -->
+          <!--     <li>Praesent commodo cursus magna, vel scelerisque nisl 
consectetur et.</li> -->
+          <!--     <li>Donec id elit non mi porta gravida at eget metus.</li> 
-->
+          <!--     <li>Nulla vitae elit libero, a pharetra augue.</li> -->
+          <!--   </ul> -->
+          <!--   <p>Donec ullamcorper nulla non metus auctor fringilla. Nulla 
vitae elit libero, a pharetra augue.</p> -->
+          <!--   <ol> -->
+          <!--     <li>Vestibulum id ligula porta felis euismod semper.</li> 
-->
+          <!--     <li>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</li> -->
+          <!--     <li>Maecenas sed diam eget risus varius blandit sit amet 
non magna.</li> -->
+          <!--   </ol> -->
+          <!--   <p>Cras mattis consectetur purus sit amet fermentum. Sed 
posuere consectetur est at lobortis.</p> -->
+          <!-- </div><\!-- /.blog-post -\-> -->
+
+        </div>
+
+      </div><!-- /.row -->
+
+      
+        
+    </div><!-- /.container -->
+
+    <!-- Bootstrap core JavaScript
+    ================================================== -->
+    <!-- Placed at the end of the document so the pages load faster -->
+    <script 
src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js";></script>
+    <script src="../../dist/js/bootstrap.min.js"></script>
+    <!-- <script src="../../assets/js/docs.min.js"></script> -->
+    <!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
+    <!-- <script 
src="../../assets/js/ie10-viewport-bug-workaround.js"></script>
+    -->
+
+    <!-- Start of StatCounter Code for Default Guide -->
+    <script type="text/javascript">
+      var sc_project=8264132; 
+      var sc_invisible=1; 
+      var sc_security="4b97fe2d"; 
+    </script>
+    <script type="text/javascript" 
src="http://www.statcounter.com/counter/counter.js";></script>
+    <noscript>
+      <div class="statcounter">
+        <a title="hit counter joomla" 
+           href="http://statcounter.com/joomla/";
+           target="_blank">
+          <img class="statcounter"
+               src="http://c.statcounter.com/8264132/0/4b97fe2d/1/";
+               alt="hit counter joomla" />
+        </a>
+      </div>
+    </noscript>
+    <!-- End of StatCounter Code for Default Guide -->
+  </body>
+</html>
+

http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6/index.html
----------------------------------------------------------------------
diff --git a/6/index.html b/6/index.html
new file mode 100644
index 0000000..7392541
--- /dev/null
+++ b/6/index.html
@@ -0,0 +1,210 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="description" content="">
+    <meta name="author" content="">
+    <link rel="icon" href="../../favicon.ico">
+
+    <title>Joshua Documentation | Joshua documentation</title>
+
+    <!-- Bootstrap core CSS -->
+    <link href="/dist/css/bootstrap.min.css" rel="stylesheet">
+
+    <!-- Custom styles for this template -->
+    <link href="/joshua6.css" rel="stylesheet">
+  </head>
+
+  <body>
+
+    <div class="blog-masthead">
+      <div class="container">
+        <nav class="blog-nav">
+          <!-- <a class="blog-nav-item active" href="#">Joshua</a> -->
+          <a class="blog-nav-item" href="/">Joshua</a>
+          <!-- <a class="blog-nav-item" href="/6.0/whats-new.html">New 
features</a> -->
+          <a class="blog-nav-item" href="/language-packs/">Language packs</a>
+          <a class="blog-nav-item" href="/data/">Datasets</a>
+          <a class="blog-nav-item" href="/support/">Support</a>
+          <a class="blog-nav-item" href="/contributors.html">Contributors</a>
+        </nav>
+      </div>
+    </div>
+
+    <div class="container">
+
+      <div class="row">
+
+        <div class="col-sm-2">
+          <div class="sidebar-module">
+            <!-- <h4>About</h4> -->
+            <center>
+            <img src="/images/joshua-logo-small.png" />
+            <p>Joshua machine translation toolkit</p>
+            </center>
+          </div>
+          <hr>
+          <center>
+            <a href="/releases/current/" target="_blank"><button 
class="button">Download Joshua 6.0.5</button></a>
+            <br />
+            <a href="/releases/runtime/" target="_blank"><button 
class="button">Runtime only version</button></a>
+            <p>Released November 5, 2015</p>
+          </center>
+          <hr>
+          <!-- <div class="sidebar-module"> -->
+          <!--   <span id="download"> -->
+          <!--     <a 
href="http://joshua-decoder.org/downloads/joshua-6.0.tgz";>Download</a> -->
+          <!--   </span> -->
+          <!-- </div> -->
+          <div class="sidebar-module">
+            <h4>Using Joshua</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/install.html">Installation</a></li>
+              <li><a href="/6.0/quick-start.html">Quick Start</a></li>
+            </ol>
+          </div>
+          <hr>
+          <div class="sidebar-module">
+            <h4>Building new models</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/pipeline.html">Pipeline</a></li>
+              <li><a href="/6.0/tutorial.html">Tutorial</a></li>
+              <li><a href="/6.0/faq.html">FAQ</a></li>
+            </ol>
+          </div>
+<!--
+          <div class="sidebar-module">
+            <h4>Phrase-based</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/phrase.html">Training</a></li>
+            </ol>
+          </div>
+-->
+          <hr>
+          <div class="sidebar-module">
+            <h4>Advanced</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/bundle.html">Building language packs</a></li>
+              <li><a href="/6.0/decoder.html">Decoder options</a></li>
+              <li><a href="/6.0/file-formats.html">File formats</a></li>
+              <li><a href="/6.0/packing.html">Packing TMs</a></li>
+              <li><a href="/6.0/large-lms.html">Building large LMs</a></li>
+            </ol>
+          </div>
+
+          <hr> 
+          <div class="sidebar-module">
+            <h4>Developer</h4>
+            <ol class="list-unstyled">              
+               <li><a 
href="https://github.com/joshua-decoder/joshua";>Github</a></li>
+               <li><a 
href="http://cs.jhu.edu/~post/joshua-docs";>Javadoc</a></li>
+               <li><a 
href="https://groups.google.com/forum/?fromgroups#!forum/joshua_developers";>Mailing
 list</a></li>              
+            </ol>
+          </div>
+
+        </div><!-- /.blog-sidebar -->
+
+        
+        <div class="col-sm-8 blog-main">
+        
+
+          <div class="blog-title">
+            <h2>Joshua documentation</h2>
+          </div>
+          
+          <div class="blog-post">
+
+            <p>This page contains end-user oriented documentation for the 6.0 
release of
+<a href="http://joshua-decoder.org/";>the Joshua decoder</a>.</p>
+
+<p>To navigate the documentation, use the links on the navigation bar to
+the left. For more detail on the decoder itself, including its command-line 
options, see
+<a href="decoder.html">the Joshua decoder page</a>.  You can also learn more 
about other steps of
+<a href="pipeline.html">the Joshua MT pipeline</a>, including <a 
href="thrax.html">grammar extraction</a> with Thrax and
+Joshua’s <a href="packing.html">efficient grammar representation</a>.</p>
+
+<p>A <a href="bundle.html">bundled configuration</a>, which is a minimal set 
of configuration, resource, and script files, can be created and easily 
transferred and shared.</p>
+
+<h2 id="development">Development</h2>
+
+<p>For developer support, please consult <a 
href="http://cs.jhu.edu/~post/joshua-docs";>the javadoc documentation</a> and 
the <a 
href="https://groups.google.com/forum/?fromgroups#!forum/joshua_developers";>Joshua
 developers mailing list</a>.</p>
+
+<h2 id="support">Support</h2>
+
+<p>If you have problems or issues, you might find some help <a 
href="faq.html">on our answers page</a> or
+<a href="https://groups.google.com/forum/?fromgroups#!forum/joshua_support";>in 
the mailing list archives</a>.</p>
+
+
+          <!--   <h4 class="blog-post-title">Welcome to Joshua!</h4> -->
+
+          <!--   <p>This blog post shows a few different types of content 
that's supported and styled with Bootstrap. Basic typography, images, and code 
are all supported.</p> -->
+          <!--   <hr> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis <a href="#">dis 
parturient montes</a>, nascetur ridiculus mus. Aenean eu leo quam. Pellentesque 
ornare sem lacinia quam venenatis vestibulum. Sed posuere consectetur est at 
lobortis. Cras mattis consectetur purus sit amet fermentum.</p> -->
+          <!--   <blockquote> -->
+          <!--     <p>Curabitur blandit tempus porttitor. <strong>Nullam quis 
risus eget urna mollis</strong> ornare vel eu leo. Nullam id dolor id nibh 
ultricies vehicula ut id elit.</p> -->
+          <!--   </blockquote> -->
+          <!--   <p>Etiam porta <em>sem malesuada magna</em> mollis euismod. 
Cras mattis consectetur purus sit amet fermentum. Aenean lacinia bibendum nulla 
sed consectetur.</p> -->
+          <!--   <h2>Heading</h2> -->
+          <!--   <p>Vivamus sagittis lacus vel augue laoreet rutrum faucibus 
dolor auctor. Duis mollis, est non commodo luctus, nisi erat porttitor ligula, 
eget lacinia odio sem nec elit. Morbi leo risus, porta ac consectetur ac, 
vestibulum at eros.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</p> -->
+          <!--   <pre><code>Example code block</code></pre> -->
+          <!--   <p>Aenean lacinia bibendum nulla sed consectetur. Etiam porta 
sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus commodo, 
tortor mauris condimentum nibh, ut fermentum massa.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus. Aenean lacinia bibendum nulla sed consectetur. 
Etiam porta sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus 
commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet 
risus.</p> -->
+          <!--   <ul> -->
+          <!--     <li>Praesent commodo cursus magna, vel scelerisque nisl 
consectetur et.</li> -->
+          <!--     <li>Donec id elit non mi porta gravida at eget metus.</li> 
-->
+          <!--     <li>Nulla vitae elit libero, a pharetra augue.</li> -->
+          <!--   </ul> -->
+          <!--   <p>Donec ullamcorper nulla non metus auctor fringilla. Nulla 
vitae elit libero, a pharetra augue.</p> -->
+          <!--   <ol> -->
+          <!--     <li>Vestibulum id ligula porta felis euismod semper.</li> 
-->
+          <!--     <li>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</li> -->
+          <!--     <li>Maecenas sed diam eget risus varius blandit sit amet 
non magna.</li> -->
+          <!--   </ol> -->
+          <!--   <p>Cras mattis consectetur purus sit amet fermentum. Sed 
posuere consectetur est at lobortis.</p> -->
+          <!-- </div><\!-- /.blog-post -\-> -->
+
+        </div>
+
+      </div><!-- /.row -->
+
+      
+        
+    </div><!-- /.container -->
+
+    <!-- Bootstrap core JavaScript
+    ================================================== -->
+    <!-- Placed at the end of the document so the pages load faster -->
+    <script 
src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js";></script>
+    <script src="../../dist/js/bootstrap.min.js"></script>
+    <!-- <script src="../../assets/js/docs.min.js"></script> -->
+    <!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
+    <!-- <script 
src="../../assets/js/ie10-viewport-bug-workaround.js"></script>
+    -->
+
+    <!-- Start of StatCounter Code for Default Guide -->
+    <script type="text/javascript">
+      var sc_project=8264132; 
+      var sc_invisible=1; 
+      var sc_security="4b97fe2d"; 
+    </script>
+    <script type="text/javascript" 
src="http://www.statcounter.com/counter/counter.js";></script>
+    <noscript>
+      <div class="statcounter">
+        <a title="hit counter joomla" 
+           href="http://statcounter.com/joomla/";
+           target="_blank">
+          <img class="statcounter"
+               src="http://c.statcounter.com/8264132/0/4b97fe2d/1/";
+               alt="hit counter joomla" />
+        </a>
+      </div>
+    </noscript>
+    <!-- End of StatCounter Code for Default Guide -->
+  </body>
+</html>
+

http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6/install.html
----------------------------------------------------------------------
diff --git a/6/install.html b/6/install.html
new file mode 100644
index 0000000..b972e81
--- /dev/null
+++ b/6/install.html
@@ -0,0 +1,301 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="description" content="">
+    <meta name="author" content="">
+    <link rel="icon" href="../../favicon.ico">
+
+    <title>Joshua Documentation | Installation</title>
+
+    <!-- Bootstrap core CSS -->
+    <link href="/dist/css/bootstrap.min.css" rel="stylesheet">
+
+    <!-- Custom styles for this template -->
+    <link href="/joshua6.css" rel="stylesheet">
+  </head>
+
+  <body>
+
+    <div class="blog-masthead">
+      <div class="container">
+        <nav class="blog-nav">
+          <!-- <a class="blog-nav-item active" href="#">Joshua</a> -->
+          <a class="blog-nav-item" href="/">Joshua</a>
+          <!-- <a class="blog-nav-item" href="/6.0/whats-new.html">New 
features</a> -->
+          <a class="blog-nav-item" href="/language-packs/">Language packs</a>
+          <a class="blog-nav-item" href="/data/">Datasets</a>
+          <a class="blog-nav-item" href="/support/">Support</a>
+          <a class="blog-nav-item" href="/contributors.html">Contributors</a>
+        </nav>
+      </div>
+    </div>
+
+    <div class="container">
+
+      <div class="row">
+
+        <div class="col-sm-2">
+          <div class="sidebar-module">
+            <!-- <h4>About</h4> -->
+            <center>
+            <img src="/images/joshua-logo-small.png" />
+            <p>Joshua machine translation toolkit</p>
+            </center>
+          </div>
+          <hr>
+          <center>
+            <a href="/releases/current/" target="_blank"><button 
class="button">Download Joshua 6.0.5</button></a>
+            <br />
+            <a href="/releases/runtime/" target="_blank"><button 
class="button">Runtime only version</button></a>
+            <p>Released November 5, 2015</p>
+          </center>
+          <hr>
+          <!-- <div class="sidebar-module"> -->
+          <!--   <span id="download"> -->
+          <!--     <a 
href="http://joshua-decoder.org/downloads/joshua-6.0.tgz";>Download</a> -->
+          <!--   </span> -->
+          <!-- </div> -->
+          <div class="sidebar-module">
+            <h4>Using Joshua</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/install.html">Installation</a></li>
+              <li><a href="/6.0/quick-start.html">Quick Start</a></li>
+            </ol>
+          </div>
+          <hr>
+          <div class="sidebar-module">
+            <h4>Building new models</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/pipeline.html">Pipeline</a></li>
+              <li><a href="/6.0/tutorial.html">Tutorial</a></li>
+              <li><a href="/6.0/faq.html">FAQ</a></li>
+            </ol>
+          </div>
+<!--
+          <div class="sidebar-module">
+            <h4>Phrase-based</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/phrase.html">Training</a></li>
+            </ol>
+          </div>
+-->
+          <hr>
+          <div class="sidebar-module">
+            <h4>Advanced</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/bundle.html">Building language packs</a></li>
+              <li><a href="/6.0/decoder.html">Decoder options</a></li>
+              <li><a href="/6.0/file-formats.html">File formats</a></li>
+              <li><a href="/6.0/packing.html">Packing TMs</a></li>
+              <li><a href="/6.0/large-lms.html">Building large LMs</a></li>
+            </ol>
+          </div>
+
+          <hr> 
+          <div class="sidebar-module">
+            <h4>Developer</h4>
+            <ol class="list-unstyled">              
+               <li><a 
href="https://github.com/joshua-decoder/joshua";>Github</a></li>
+               <li><a 
href="http://cs.jhu.edu/~post/joshua-docs";>Javadoc</a></li>
+               <li><a 
href="https://groups.google.com/forum/?fromgroups#!forum/joshua_developers";>Mailing
 list</a></li>              
+            </ol>
+          </div>
+
+        </div><!-- /.blog-sidebar -->
+
+        
+        <div class="col-sm-8 blog-main">
+        
+
+          <div class="blog-title">
+            <h2>Installation</h2>
+          </div>
+          
+          <div class="blog-post">
+
+            <h3 id="download-and-install">Download and install</h3>
+
+<p>To use Joshua as a standalone decoder (with <a 
href="/language-packs/">language packs</a>), you only need to download and 
install the runtime version of the decoder. 
+If you also wish to build translation models from your own data, you will want 
to install the full version.
+See the instructions below.</p>
+
+<ol>
+  <li>
+    <p>Set up some basic environment variables. 
+You need to define <code class="highlighter-rouge">$JAVA_HOME</code></p>
+
+    <div class="highlighter-rouge"><pre class="highlight"><code>export 
JAVA_HOME=/path/to/java
+
+# JAVA_HOME is not very standardized. Here are some places to look:
+# OS X:  export 
JAVA_HOME=/Library/Java/JavaVirtualMachines/jdk1.7.0_71.jdk/Contents/Home
+# Linux: export JAVA_HOME=/usr/java/default
+</code></pre>
+    </div>
+  </li>
+  <li>
+    <p>If you are installing the full version of Joshua, you also need to 
define <code class="highlighter-rouge">$HADOOP</code> to point to your Hadoop 
installation.
+(Joshua looks for the Hadoop executuble in <code 
class="highlighter-rouge">$HADOOP/bin/hadoop</code>)</p>
+
+    <div class="highlighter-rouge"><pre class="highlight"><code>export 
HADOOP=/usr
+</code></pre>
+    </div>
+
+    <p>If you don’t have a Hadoop installation, <a 
href="pipeline.html">Joshua’s pipeline</a> can install a standalone version 
for you.</p>
+  </li>
+  <li>
+    <p>To install just the runtime version of Joshua, type</p>
+
+    <div class="highlighter-rouge"><pre class="highlight"><code>wget -q 
http://cs.jhu.edu/~post/files/joshua-runtime-6.0.5.tgz
+</code></pre>
+    </div>
+
+    <p>Then build everything</p>
+
+    <div class="highlighter-rouge"><pre class="highlight"><code>tar xzf 
joshua-runtime-6.0.5.tgz
+cd joshua-runtime-6.0.5
+
+# Add this to your init files
+export JOSHUA=$(pwd)
+   
+# build everything
+ant
+</code></pre>
+    </div>
+  </li>
+  <li>
+    <p>To instead install the full version, type</p>
+
+    <div class="highlighter-rouge"><pre class="highlight"><code>wget -q 
http://cs.jhu.edu/~post/files/joshua-6.0.5.tgz
+
+tar xzf joshua-6.0.5.tgz
+cd joshua-6.0.5
+
+# Add this to your init files
+export JOSHUA=$(pwd)
+   
+# build everything
+ant
+</code></pre>
+    </div>
+  </li>
+</ol>
+
+<h3 id="building-new-models">Building new models</h3>
+
+<p>If you wish to build models for new language pairs from existing data (such 
as the <a href="http://statmt.org/wmt14/";>WMT data</a>), you need to install 
some additional dependencies.</p>
+
+<ol>
+  <li>
+    <p>For learning hierarchical models, Joshua includes a tool called <a 
href="thrax.html">Thrax</a>, which
+is built on Hadoop. If you have a Hadoop installation, make sure that the 
environment variable
+<code class="highlighter-rouge">$HADOOP</code> is set and points to it. If you 
don’t, Joshua will roll one out for you in standalone
+mode. Hadoop is only needed if you plan to build new models with Joshua.</p>
+  </li>
+  <li>
+    <p>You will need to install Moses if either of the following applies to 
you:</p>
+
+    <ul>
+      <li>
+        <p>You wish to build <a href="phrase.html">phrase-based models</a> 
(Joshua 6 includes a phrase-based
+decoder, but not the tools for building such a model)</p>
+      </li>
+      <li>
+        <p>You are building your own models (phrase- or syntax-based) and wish 
to use Cherry &amp; Foster’s
+<a href="http://aclweb.org/anthology-new/N/N12/N12-1047v2.pdf";>batch MIRA 
tuner</a> instead of the included
+MERT implementation, <a href="zmert.html">Z-MERT</a>. </p>
+      </li>
+    </ul>
+
+    <p>Follow <a 
href="http://www.statmt.org/moses/?n=Development.GetStarted";>the instructions 
for installing Moses
+here</a>, and then define the <code class="highlighter-rouge">$MOSES</code>
+environment variable to point to the root of the Moses installation.</p>
+  </li>
+</ol>
+
+<h2 id="more-information">More information</h2>
+
+<p>For more detail on the decoder itself, including its command-line options, 
see
+<a href="decoder.html">the Joshua decoder page</a>.  You can also learn more 
about other steps of
+<a href="pipeline.html">the Joshua MT pipeline</a>, including <a 
href="thrax.html">grammar extraction</a> with Thrax and
+Joshua’s <a href="packing.html">efficient grammar representation</a>.</p>
+
+<p>If you have problems or issues, you might find some help <a 
href="faq.html">on our answers page</a> or
+<a href="https://groups.google.com/forum/?fromgroups#!forum/joshua_support";>in 
the mailing list archives</a>.</p>
+
+<p>A <a href="bundle.html">bundled configuration</a>, which is a minimal set 
of configuration, resource, and script files, can be created and easily 
transferred and shared.</p>
+
+
+          <!--   <h4 class="blog-post-title">Welcome to Joshua!</h4> -->
+
+          <!--   <p>This blog post shows a few different types of content 
that's supported and styled with Bootstrap. Basic typography, images, and code 
are all supported.</p> -->
+          <!--   <hr> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis <a href="#">dis 
parturient montes</a>, nascetur ridiculus mus. Aenean eu leo quam. Pellentesque 
ornare sem lacinia quam venenatis vestibulum. Sed posuere consectetur est at 
lobortis. Cras mattis consectetur purus sit amet fermentum.</p> -->
+          <!--   <blockquote> -->
+          <!--     <p>Curabitur blandit tempus porttitor. <strong>Nullam quis 
risus eget urna mollis</strong> ornare vel eu leo. Nullam id dolor id nibh 
ultricies vehicula ut id elit.</p> -->
+          <!--   </blockquote> -->
+          <!--   <p>Etiam porta <em>sem malesuada magna</em> mollis euismod. 
Cras mattis consectetur purus sit amet fermentum. Aenean lacinia bibendum nulla 
sed consectetur.</p> -->
+          <!--   <h2>Heading</h2> -->
+          <!--   <p>Vivamus sagittis lacus vel augue laoreet rutrum faucibus 
dolor auctor. Duis mollis, est non commodo luctus, nisi erat porttitor ligula, 
eget lacinia odio sem nec elit. Morbi leo risus, porta ac consectetur ac, 
vestibulum at eros.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</p> -->
+          <!--   <pre><code>Example code block</code></pre> -->
+          <!--   <p>Aenean lacinia bibendum nulla sed consectetur. Etiam porta 
sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus commodo, 
tortor mauris condimentum nibh, ut fermentum massa.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus. Aenean lacinia bibendum nulla sed consectetur. 
Etiam porta sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus 
commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet 
risus.</p> -->
+          <!--   <ul> -->
+          <!--     <li>Praesent commodo cursus magna, vel scelerisque nisl 
consectetur et.</li> -->
+          <!--     <li>Donec id elit non mi porta gravida at eget metus.</li> 
-->
+          <!--     <li>Nulla vitae elit libero, a pharetra augue.</li> -->
+          <!--   </ul> -->
+          <!--   <p>Donec ullamcorper nulla non metus auctor fringilla. Nulla 
vitae elit libero, a pharetra augue.</p> -->
+          <!--   <ol> -->
+          <!--     <li>Vestibulum id ligula porta felis euismod semper.</li> 
-->
+          <!--     <li>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</li> -->
+          <!--     <li>Maecenas sed diam eget risus varius blandit sit amet 
non magna.</li> -->
+          <!--   </ol> -->
+          <!--   <p>Cras mattis consectetur purus sit amet fermentum. Sed 
posuere consectetur est at lobortis.</p> -->
+          <!-- </div><\!-- /.blog-post -\-> -->
+
+        </div>
+
+      </div><!-- /.row -->
+
+      
+        
+    </div><!-- /.container -->
+
+    <!-- Bootstrap core JavaScript
+    ================================================== -->
+    <!-- Placed at the end of the document so the pages load faster -->
+    <script 
src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js";></script>
+    <script src="../../dist/js/bootstrap.min.js"></script>
+    <!-- <script src="../../assets/js/docs.min.js"></script> -->
+    <!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
+    <!-- <script 
src="../../assets/js/ie10-viewport-bug-workaround.js"></script>
+    -->
+
+    <!-- Start of StatCounter Code for Default Guide -->
+    <script type="text/javascript">
+      var sc_project=8264132; 
+      var sc_invisible=1; 
+      var sc_security="4b97fe2d"; 
+    </script>
+    <script type="text/javascript" 
src="http://www.statcounter.com/counter/counter.js";></script>
+    <noscript>
+      <div class="statcounter">
+        <a title="hit counter joomla" 
+           href="http://statcounter.com/joomla/";
+           target="_blank">
+          <img class="statcounter"
+               src="http://c.statcounter.com/8264132/0/4b97fe2d/1/";
+               alt="hit counter joomla" />
+        </a>
+      </div>
+    </noscript>
+    <!-- End of StatCounter Code for Default Guide -->
+  </body>
+</html>
+

http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6/jacana.html
----------------------------------------------------------------------
diff --git a/6/jacana.html b/6/jacana.html
new file mode 100644
index 0000000..b8f5a79
--- /dev/null
+++ b/6/jacana.html
@@ -0,0 +1,331 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="description" content="">
+    <meta name="author" content="">
+    <link rel="icon" href="../../favicon.ico">
+
+    <title>Joshua Documentation | Alignment with Jacana</title>
+
+    <!-- Bootstrap core CSS -->
+    <link href="/dist/css/bootstrap.min.css" rel="stylesheet">
+
+    <!-- Custom styles for this template -->
+    <link href="/joshua6.css" rel="stylesheet">
+  </head>
+
+  <body>
+
+    <div class="blog-masthead">
+      <div class="container">
+        <nav class="blog-nav">
+          <!-- <a class="blog-nav-item active" href="#">Joshua</a> -->
+          <a class="blog-nav-item" href="/">Joshua</a>
+          <!-- <a class="blog-nav-item" href="/6.0/whats-new.html">New 
features</a> -->
+          <a class="blog-nav-item" href="/language-packs/">Language packs</a>
+          <a class="blog-nav-item" href="/data/">Datasets</a>
+          <a class="blog-nav-item" href="/support/">Support</a>
+          <a class="blog-nav-item" href="/contributors.html">Contributors</a>
+        </nav>
+      </div>
+    </div>
+
+    <div class="container">
+
+      <div class="row">
+
+        <div class="col-sm-2">
+          <div class="sidebar-module">
+            <!-- <h4>About</h4> -->
+            <center>
+            <img src="/images/joshua-logo-small.png" />
+            <p>Joshua machine translation toolkit</p>
+            </center>
+          </div>
+          <hr>
+          <center>
+            <a href="/releases/current/" target="_blank"><button 
class="button">Download Joshua 6.0.5</button></a>
+            <br />
+            <a href="/releases/runtime/" target="_blank"><button 
class="button">Runtime only version</button></a>
+            <p>Released November 5, 2015</p>
+          </center>
+          <hr>
+          <!-- <div class="sidebar-module"> -->
+          <!--   <span id="download"> -->
+          <!--     <a 
href="http://joshua-decoder.org/downloads/joshua-6.0.tgz";>Download</a> -->
+          <!--   </span> -->
+          <!-- </div> -->
+          <div class="sidebar-module">
+            <h4>Using Joshua</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/install.html">Installation</a></li>
+              <li><a href="/6.0/quick-start.html">Quick Start</a></li>
+            </ol>
+          </div>
+          <hr>
+          <div class="sidebar-module">
+            <h4>Building new models</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/pipeline.html">Pipeline</a></li>
+              <li><a href="/6.0/tutorial.html">Tutorial</a></li>
+              <li><a href="/6.0/faq.html">FAQ</a></li>
+            </ol>
+          </div>
+<!--
+          <div class="sidebar-module">
+            <h4>Phrase-based</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/phrase.html">Training</a></li>
+            </ol>
+          </div>
+-->
+          <hr>
+          <div class="sidebar-module">
+            <h4>Advanced</h4>
+            <ol class="list-unstyled">
+              <li><a href="/6.0/bundle.html">Building language packs</a></li>
+              <li><a href="/6.0/decoder.html">Decoder options</a></li>
+              <li><a href="/6.0/file-formats.html">File formats</a></li>
+              <li><a href="/6.0/packing.html">Packing TMs</a></li>
+              <li><a href="/6.0/large-lms.html">Building large LMs</a></li>
+            </ol>
+          </div>
+
+          <hr> 
+          <div class="sidebar-module">
+            <h4>Developer</h4>
+            <ol class="list-unstyled">              
+               <li><a 
href="https://github.com/joshua-decoder/joshua";>Github</a></li>
+               <li><a 
href="http://cs.jhu.edu/~post/joshua-docs";>Javadoc</a></li>
+               <li><a 
href="https://groups.google.com/forum/?fromgroups#!forum/joshua_developers";>Mailing
 list</a></li>              
+            </ol>
+          </div>
+
+        </div><!-- /.blog-sidebar -->
+
+        
+        <div class="col-sm-8 blog-main">
+        
+
+          <div class="blog-title">
+            <h2>Alignment with Jacana</h2>
+          </div>
+          
+          <div class="blog-post">
+
+            <h2 id="introduction">Introduction</h2>
+
+<p>jacana-xy is a token-based word aligner for machine translation, adapted 
from the original
+English-English word aligner jacana-align described in the following paper:</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>A Lightweight and 
High Performance Monolingual Word Aligner. Xuchen Yao, Benjamin Van Durme,
+Chris Callison-Burch and Peter Clark. Proceedings of ACL 2013, short papers.
+</code></pre>
+</div>
+
+<p>It currently supports only aligning from French to English with a very 
limited feature set, from the
+one week hack at the <a href="http://statmt.org/mtm13";>Eighth MT Marathon 
2013</a>. Please feel free to check
+out the code, read to the bottom of this page, and
+<a href="http://www.cs.jhu.edu/~xuchen/";>send the author an email</a> if you 
want to add more language pairs to
+it.</p>
+
+<h2 id="build">Build</h2>
+
+<p>jacana-xy is written in a mixture of Java and Scala. If you build from ant, 
you have to set up the
+environmental variables <code class="highlighter-rouge">JAVA_HOME</code> and 
<code class="highlighter-rouge">SCALA_HOME</code>. In my system, I have:</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>export 
JAVA_HOME=/usr/lib/jvm/java-6-sun-1.6.0.26
+export SCALA_HOME=/home/xuchen/Downloads/scala-2.10.2
+</code></pre>
+</div>
+
+<p>Then type:</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>ant
+</code></pre>
+</div>
+
+<p>build/lib/jacana-xy.jar will be built for you.</p>
+
+<p>If you build from Eclipse, first install scala-ide, then import the whole 
jacana folder as a Scala project. Eclipse should find the .project file and set 
up the project automatically for you.</p>
+
+<p>Demo
+scripts-align/runDemoServer.sh shows up the web demo. Direct your browser to 
http://localhost:8080/ and you should be able to align some sentences.</p>
+
+<p>Note: To make jacana-xy know where to look for resource files, pass the 
property JACANA_HOME with Java when you run it:</p>
+
+<p>java -DJACANA_HOME=/path/to/jacana -cp jacana-xy.jar ……</p>
+
+<p>Browser
+You can also browse one or two alignment files (*.json) with firefox opening 
src/web/AlignmentBrowser.html:</p>
+
+<p>Note 1: due to strict security setting for accessing local files, Chrome/IE 
won’t work.</p>
+
+<p>Note 2: the input *.json files have to be in the same folder with 
AlignmentBrowser.html.</p>
+
+<p>Align
+scripts-align/alignFile.sh aligns tab-separated sentence files and outputs the 
output to a .json file that’s accepted by the browser:</p>
+
+<p>java -DJACANA_HOME=../ -jar ../build/lib/jacana-xy.jar -src fr -tgt en -m 
fr-en.model -a s.txt -o s.json</p>
+
+<p>scripts-align/alignFile.sh takes GIZA++-style input files (one file 
containing the source sentences, and the other file the target sentences) and 
outputs to one .align file with dashed alignment indices (e.g. “1-2 
0-4”):</p>
+
+<p>java -DJACANA_HOME=../ -jar ../build/lib/jacana-xy.jar -m fr-en.model -src 
fr -tgt en -a s1.txt -b s2.txt -o s.align</p>
+
+<p>Training
+java -DJACANA_HOME=../ -jar ../build/lib/jacana-xy.jar -r train.json -d 
dev.json -t test.json -m /tmp/align.model</p>
+
+<p>The aligner then would train on train.json, and report F1 values on 
dev.json for every 10 iterations, when the stopping criterion has reached, it 
will test on test.json.</p>
+
+<p>For every 10 iterations, a model file is saved to (in this example) 
/tmp/align.model.iter_XX.F1_XX.X. Normally what I do is to select the one with 
the best F1 on dev.json, then run a final test on test.json:</p>
+
+<p>java -DJACANA_HOME=../ -jar ../build/lib/jacana-xy.jar -t test.json -m 
/tmp/align.model.iter_XX.F1_XX.X</p>
+
+<p>In this case since the training data is missing, the aligner assumes it’s 
a test job, then reads model file still from the -m option, and test on 
test.json.</p>
+
+<p>All the json files are in a format like the following (also accepted by the 
browser for display):</p>
+
+<p>[
+    {
+        “id”: “0008”,
+        “name”: “Hansards.french-english.0008”,
+        “possibleAlign”: “0-0 0-1 0-2”,
+        “source”: “bravo !”,
+        “sureAlign”: “1-3”,
+        “target”: “hear , hear !”
+    },
+    {
+        “id”: “0009”,
+        “name”: “Hansards.french-english.0009”,
+        “possibleAlign”: “1-1 6-5 7-5 6-6 7-6 13-10 13-11”,
+        “source”: “monsieur le Orateur , ma question se adresse à le 
ministre chargé de les transports .”,
+        “sureAlign”: “0-0 2-1 3-2 4-3 5-4 8-7 9-8 10-9 12-10 14-11 
15-12”,
+        “target”: “Mr. Speaker , my question is directed to the Minister 
of Transport .”
+    }
+]
+Where possibleAlign is not used.</p>
+
+<p>The stopping criterion is to run up to 300 iterations or when the objective 
difference between two iterations is less than 0.001, whichever happens first. 
Currently they are hard-coded. If you need to be flexible on this, send me an 
email!</p>
+
+<p>Support More Languages
+To add support to more languages, you need:</p>
+
+<p>labelled word alignment (in the download there’s already French-English 
under alignment-data/fr-en; I also have Chinese-English and Arabic-English; let 
me know if you have more). Usually 100 labelled sentence pairs would be enough
+implement some feature functions for this language pair
+To add more features, you need to implement the following interface:</p>
+
+<p>edu.jhu.jacana.align.feature.AlignFeature</p>
+
+<p>and override the following function:</p>
+
+<p>addPhraseBasedFeature</p>
+
+<p>For instance, a simple feature that checks whether the two words are 
translations in wiktionary for the French-English alignment task has the 
function implemented as:</p>
+
+<p>def addPhraseBasedFeature(pair: AlignPair, ins:AlignFeatureVector, i:Int, 
srcSpan:Int, j:Int, tgtSpan:Int,
+      currState:Int, featureAlphabet: Alphabet){
+  if (j == -1) {
+  } else {
+    val srcTokens = pair.srcTokens.slice(i, i+srcSpan).mkString(“ “)
+    val tgtTokens = pair.tgtTokens.slice(j, j+tgtSpan).mkString(“ “)</p>
+
+<div class="highlighter-rouge"><pre class="highlight"><code>if 
(WiktionaryMultilingual.exists(srcTokens, tgtTokens)) {
+  ins.addFeature("InWiktionary", NONE_STATE, currState, 1.0, srcSpan, 
featureAlphabet) 
+}
+</code></pre>
+</div>
+
+<p>}     <br />
+}
+This is a more general function that also deals with phrase alignment. But it 
is suggested to implement it just for token alignment as currently the phrase 
alignment part is very slow to train (60x slower than token alignment).</p>
+
+<p>Some other language-independent and English-only features are implemented 
under the package edu.jhu.jacana.align.feature, for instance:</p>
+
+<p>StringSimilarityAlignFeature: various string similarity measures</p>
+
+<p>PositionalAlignFeature: features based on relative sentence positions</p>
+
+<p>DistortionAlignFeature: Markovian (state transition) features</p>
+
+<p>When you add features for more languages, just create a new package like 
the one for French-English:</p>
+
+<p>edu.jhu.jacana.align.feature.fr_en</p>
+
+<p>and start coding!</p>
+
+
+
+          <!--   <h4 class="blog-post-title">Welcome to Joshua!</h4> -->
+
+          <!--   <p>This blog post shows a few different types of content 
that's supported and styled with Bootstrap. Basic typography, images, and code 
are all supported.</p> -->
+          <!--   <hr> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis <a href="#">dis 
parturient montes</a>, nascetur ridiculus mus. Aenean eu leo quam. Pellentesque 
ornare sem lacinia quam venenatis vestibulum. Sed posuere consectetur est at 
lobortis. Cras mattis consectetur purus sit amet fermentum.</p> -->
+          <!--   <blockquote> -->
+          <!--     <p>Curabitur blandit tempus porttitor. <strong>Nullam quis 
risus eget urna mollis</strong> ornare vel eu leo. Nullam id dolor id nibh 
ultricies vehicula ut id elit.</p> -->
+          <!--   </blockquote> -->
+          <!--   <p>Etiam porta <em>sem malesuada magna</em> mollis euismod. 
Cras mattis consectetur purus sit amet fermentum. Aenean lacinia bibendum nulla 
sed consectetur.</p> -->
+          <!--   <h2>Heading</h2> -->
+          <!--   <p>Vivamus sagittis lacus vel augue laoreet rutrum faucibus 
dolor auctor. Duis mollis, est non commodo luctus, nisi erat porttitor ligula, 
eget lacinia odio sem nec elit. Morbi leo risus, porta ac consectetur ac, 
vestibulum at eros.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</p> -->
+          <!--   <pre><code>Example code block</code></pre> -->
+          <!--   <p>Aenean lacinia bibendum nulla sed consectetur. Etiam porta 
sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus commodo, 
tortor mauris condimentum nibh, ut fermentum massa.</p> -->
+          <!--   <h3>Sub-heading</h3> -->
+          <!--   <p>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus. Aenean lacinia bibendum nulla sed consectetur. 
Etiam porta sem malesuada magna mollis euismod. Fusce dapibus, tellus ac cursus 
commodo, tortor mauris condimentum nibh, ut fermentum massa justo sit amet 
risus.</p> -->
+          <!--   <ul> -->
+          <!--     <li>Praesent commodo cursus magna, vel scelerisque nisl 
consectetur et.</li> -->
+          <!--     <li>Donec id elit non mi porta gravida at eget metus.</li> 
-->
+          <!--     <li>Nulla vitae elit libero, a pharetra augue.</li> -->
+          <!--   </ul> -->
+          <!--   <p>Donec ullamcorper nulla non metus auctor fringilla. Nulla 
vitae elit libero, a pharetra augue.</p> -->
+          <!--   <ol> -->
+          <!--     <li>Vestibulum id ligula porta felis euismod semper.</li> 
-->
+          <!--     <li>Cum sociis natoque penatibus et magnis dis parturient 
montes, nascetur ridiculus mus.</li> -->
+          <!--     <li>Maecenas sed diam eget risus varius blandit sit amet 
non magna.</li> -->
+          <!--   </ol> -->
+          <!--   <p>Cras mattis consectetur purus sit amet fermentum. Sed 
posuere consectetur est at lobortis.</p> -->
+          <!-- </div><\!-- /.blog-post -\-> -->
+
+        </div>
+
+      </div><!-- /.row -->
+
+      
+        
+    </div><!-- /.container -->
+
+    <!-- Bootstrap core JavaScript
+    ================================================== -->
+    <!-- Placed at the end of the document so the pages load faster -->
+    <script 
src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.1/jquery.min.js";></script>
+    <script src="../../dist/js/bootstrap.min.js"></script>
+    <!-- <script src="../../assets/js/docs.min.js"></script> -->
+    <!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
+    <!-- <script 
src="../../assets/js/ie10-viewport-bug-workaround.js"></script>
+    -->
+
+    <!-- Start of StatCounter Code for Default Guide -->
+    <script type="text/javascript">
+      var sc_project=8264132; 
+      var sc_invisible=1; 
+      var sc_security="4b97fe2d"; 
+    </script>
+    <script type="text/javascript" 
src="http://www.statcounter.com/counter/counter.js";></script>
+    <noscript>
+      <div class="statcounter">
+        <a title="hit counter joomla" 
+           href="http://statcounter.com/joomla/";
+           target="_blank">
+          <img class="statcounter"
+               src="http://c.statcounter.com/8264132/0/4b97fe2d/1/";
+               alt="hit counter joomla" />
+        </a>
+      </div>
+    </noscript>
+    <!-- End of StatCounter Code for Default Guide -->
+  </body>
+</html>
+

Reply via email to