http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6.0/advanced.html ---------------------------------------------------------------------- diff --git a/6.0/advanced.html b/6.0/advanced.html new file mode 100644 index 0000000..f4a3335 --- /dev/null +++ b/6.0/advanced.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 | Advanced 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>Advanced features</h2> + </div> + + <div class="blog-post"> + + + + + <!-- <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/53cc3005/6.0/advanced.md ---------------------------------------------------------------------- diff --git a/6.0/advanced.md b/6.0/advanced.md deleted file mode 100644 index 4997e73..0000000 --- a/6.0/advanced.md +++ /dev/null @@ -1,7 +0,0 @@ ---- -layout: default6 -category: links -title: Advanced features ---- - - http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6.0/bundle.html ---------------------------------------------------------------------- diff --git a/6.0/bundle.html b/6.0/bundle.html new file mode 100644 index 0000000..1f0ee11 --- /dev/null +++ b/6.0/bundle.html @@ -0,0 +1,297 @@ +<!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 | Building a language pack</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>Building a language pack</h2> + </div> + + <div class="blog-post"> + + <p><em>The information in this page applies to Joshua 6.0.3 and greater</em>.</p> + +<p>Joshua distributes <a href="/language-packs">language packs</a>, which are models +that have been trained and tuned for particular language pairs. You +can easily create your own language pack after you have trained and +tuned a model using the provided +<code class="highlighter-rouge">$JOSHUA/scripts/support/run-bundler.py</code> script, which gathers files +from a pipeline training directory and bundles them together for easy +distribution and release.</p> + +<p>The script takes just two mandatory arguments in the following order:</p> + +<ol> + <li>The path to the Joshua configuration file to base the bundle +on. This file should contain the tuned weights from the tuning run, so +you can use either the final tuned file from the tuning run +(<code class="highlighter-rouge">tune/joshua.config.final</code>) or from the test run +(<code class="highlighter-rouge">test/model/joshua.config</code>).</li> + <li>The directory to place the language pack in. If this directory +already exists, the script will die, unless you also pass <code class="highlighter-rouge">--force</code>.</li> +</ol> + +<p>In addition, there are a number of other arguments that may be important.</p> + +<ul> + <li> + <p><code class="highlighter-rouge">--root /path/to/root</code>. If file paths in the Joshua config file are + not absolute, you need to provide relative root. If you specify a + tuned pipeline file (such as <code class="highlighter-rouge">tune/joshua.config.final</code> above), the + paths should all be absolute. If you instead provide a config file + from a previous run bundle (e.g., <code class="highlighter-rouge">test/model/joshua.config</code>), the + bundle directory above is the relative root.</p> + </li> + <li> + <p>The config file options that are used in the pipeline are likely not +the ones you want if you release a model. For example, the tuning +configuration file contains options that tell Joshua to output 300 +translation candidates for each sentence (<code class="highlighter-rouge">-top-n 300</code>) and to +include lots of detail about each translation (<code class="highlighter-rouge">-output-format '%i +||| %s ||| %f ||| %c'</code>). Because of this, you will want to tell the +run bundler to change many of the config file options to be more +geared towards human-readable output. The default copy-config +options are options are <code class="highlighter-rouge">-top-n 0 -output-format %S -mark-oovs +false</code>, which accomplishes exactly this (human readability).</p> + </li> + <li> + <p>A very important issue has to do with the translation model (the +âTMâ, also sometimes called the grammar or phrase table). The +translation model can be very large, so that it takes a long time to +load and to <a href="packing.html">pack</a>. To reduce this time during model +training, the translation model is filtered against the tuning and +testing data in the pipeline, and these filtered models will be what +is listed in the source config files. However, when exporting a +model for use as a language pack, you need to export the full model +instead of the filtered one so as to maximize your coverage on new +test data. The <code class="highlighter-rouge">--tm</code> parameter is used to accomplish this; it takes +an argument specifying the path to the full model. If you would +additionally like the large model to be <a href="packing.html">packed</a> (this +is recommended; it reformats the TM so that it can be quickly loaded +at run time), you can use <code class="highlighter-rouge">--pack-tm</code> instead. You can only pack one +TM (but typically there is only TM anyway). Multiple <code class="highlighter-rouge">--tm</code> +parameters can be passed; they will replace TMs found in the config +file in the order they are found.</p> + </li> +</ul> + +<p>Here is an example invocation for packing a hierarchical model using +the final tuned Joshua config file:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>./run-bundler.py \ + --force --verbose \ + /path/to/rundir/tune/joshua.config.final \ + language-pack-YYYY-MM-DD \ + --root /path/to/rundir \ + --pack-tm /path/to/rundir/grammar.gz \ + --copy-config-options \ + '-top-n 1 -output-format %S -mark-oovs false' \ + --server-port 5674 +</code></pre> +</div> + +<p>The copy config options tell the decoder to present just the +single-best (<code class="highlighter-rouge">-top-n 0</code>) translated output string that has been +heuristically capitalized (<code class="highlighter-rouge">-output-format %S</code>), to not append <code class="highlighter-rouge">_OOV</code> +to OOVs (<code class="highlighter-rouge">-mark-oovs false</code>), and to use the translation model +<code class="highlighter-rouge">/path/to/rundir/grammar.gz</code> as the main translation model, packing it +before placing it in the bundle. Note that these arguments to +<code class="highlighter-rouge">--copy-config</code> are the default, so you could leave this off entirely. +See <a href="decoder.html">this page</a> for a longer list of decoder options.</p> + +<p>This command is a slight variation used for phrase-based models, which +instead takes the test-set Joshua config (the result is the same):</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>./run-bundler.py \ + --force --verbose \ + /path/to/rundir/test/model/joshua.config \ + --root /path/to/rundir/test/model \ + language-pack-YYYY-MM-DD \ + --pack-tm /path/to/rundir/model/phrase-table.gz \ + --server-port 5674 +</code></pre> +</div> + +<p>In both cases, a new directory <code class="highlighter-rouge">language-pack-YYYY-MM-DD</code> will be +created along with a README and a number of support files.</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/53cc3005/6.0/bundle.md ---------------------------------------------------------------------- diff --git a/6.0/bundle.md b/6.0/bundle.md deleted file mode 100644 index f433172..0000000 --- a/6.0/bundle.md +++ /dev/null @@ -1,100 +0,0 @@ ---- -layout: default6 -category: links -title: Building a language pack ---- - -*The information in this page applies to Joshua 6.0.3 and greater*. - -Joshua distributes [language packs](/language-packs), which are models -that have been trained and tuned for particular language pairs. You -can easily create your own language pack after you have trained and -tuned a model using the provided -`$JOSHUA/scripts/support/run-bundler.py` script, which gathers files -from a pipeline training directory and bundles them together for easy -distribution and release. - -The script takes just two mandatory arguments in the following order: - -1. The path to the Joshua configuration file to base the bundle - on. This file should contain the tuned weights from the tuning run, so - you can use either the final tuned file from the tuning run - (`tune/joshua.config.final`) or from the test run - (`test/model/joshua.config`). -1. The directory to place the language pack in. If this directory - already exists, the script will die, unless you also pass `--force`. - -In addition, there are a number of other arguments that may be important. - -- `--root /path/to/root`. If file paths in the Joshua config file are - not absolute, you need to provide relative root. If you specify a - tuned pipeline file (such as `tune/joshua.config.final` above), the - paths should all be absolute. If you instead provide a config file - from a previous run bundle (e.g., `test/model/joshua.config`), the - bundle directory above is the relative root. - -- The config file options that are used in the pipeline are likely not - the ones you want if you release a model. For example, the tuning - configuration file contains options that tell Joshua to output 300 - translation candidates for each sentence (`-top-n 300`) and to - include lots of detail about each translation (`-output-format '%i - ||| %s ||| %f ||| %c'`). Because of this, you will want to tell the - run bundler to change many of the config file options to be more - geared towards human-readable output. The default copy-config - options are options are `-top-n 0 -output-format %S -mark-oovs - false`, which accomplishes exactly this (human readability). - -- A very important issue has to do with the translation model (the - "TM", also sometimes called the grammar or phrase table). The - translation model can be very large, so that it takes a long time to - load and to [pack](packing.html). To reduce this time during model - training, the translation model is filtered against the tuning and - testing data in the pipeline, and these filtered models will be what - is listed in the source config files. However, when exporting a - model for use as a language pack, you need to export the full model - instead of the filtered one so as to maximize your coverage on new - test data. The `--tm` parameter is used to accomplish this; it takes - an argument specifying the path to the full model. If you would - additionally like the large model to be [packed](packing.html) (this - is recommended; it reformats the TM so that it can be quickly loaded - at run time), you can use `--pack-tm` instead. You can only pack one - TM (but typically there is only TM anyway). Multiple `--tm` - parameters can be passed; they will replace TMs found in the config - file in the order they are found. - -Here is an example invocation for packing a hierarchical model using -the final tuned Joshua config file: - - ./run-bundler.py \ - --force --verbose \ - /path/to/rundir/tune/joshua.config.final \ - language-pack-YYYY-MM-DD \ - --root /path/to/rundir \ - --pack-tm /path/to/rundir/grammar.gz \ - --copy-config-options \ - '-top-n 1 -output-format %S -mark-oovs false' \ - --server-port 5674 - -The copy config options tell the decoder to present just the -single-best (`-top-n 0`) translated output string that has been -heuristically capitalized (`-output-format %S`), to not append `_OOV` -to OOVs (`-mark-oovs false`), and to use the translation model -`/path/to/rundir/grammar.gz` as the main translation model, packing it -before placing it in the bundle. Note that these arguments to -`--copy-config` are the default, so you could leave this off entirely. -See [this page](decoder.html) for a longer list of decoder options. - -This command is a slight variation used for phrase-based models, which -instead takes the test-set Joshua config (the result is the same): - - ./run-bundler.py \ - --force --verbose \ - /path/to/rundir/test/model/joshua.config \ - --root /path/to/rundir/test/model \ - language-pack-YYYY-MM-DD \ - --pack-tm /path/to/rundir/model/phrase-table.gz \ - --server-port 5674 - -In both cases, a new directory `language-pack-YYYY-MM-DD` will be -created along with a README and a number of support files. - http://git-wip-us.apache.org/repos/asf/incubator-joshua-site/blob/53cc3005/6.0/decoder.html ---------------------------------------------------------------------- diff --git a/6.0/decoder.html b/6.0/decoder.html new file mode 100644 index 0000000..45d238b --- /dev/null +++ b/6.0/decoder.html @@ -0,0 +1,671 @@ +<!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 | Decoder configuration parameters</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>Decoder configuration parameters</h2> + </div> + + <div class="blog-post"> + + <p>Joshua configuration parameters affect the runtime behavior of the decoder itself. This page +describes the complete list of these parameters and describes how to invoke the decoder manually.</p> + +<p>To run the decoder, a convenience script is provided that loads the necessary Java libraries. +Assuming you have set the environment variable <code class="highlighter-rouge">$JOSHUA</code> to point to the root of your installation, +its syntax is:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>$JOSHUA/bin/decoder [-m memory-amount] [-c config-file other-joshua-options ...] +</code></pre> +</div> + +<p>The <code class="highlighter-rouge">-m</code> argument, if present, must come first, and the memory specification is in Java format +(e.g., 400m, 4g, 50g). Most notably, the suffixes âmâ and âgâ are used for âmegabytesâ and +âgigabytesâ, and there cannot be a space between the number and the unit. The value of this +argument is passed to Java itself in the invocation of the decoder, and the remaining options are +passed to Joshua. The <code class="highlighter-rouge">-c</code> parameter has special import because it specifies the location of the +configuration file.</p> + +<p>The Joshua decoder works by reading from STDIN and printing translations to STDOUT as they are +received, according to a number of <a href="#output">output options</a>. If no run-time parameters are +specified (e.g., no translation model), sentences are simply pushed through untranslated. Blank +lines are similarly pushed through as blank lines, so as to maintain parallelism with the input.</p> + +<p>Parameters can be provided to Joshua via a configuration file and from the command +line. Command-line arguments override values found in the configuration file. The format for +configuration file parameters is</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>parameter = value +</code></pre> +</div> + +<p>Command-line options are specified in the following format</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>-parameter value +</code></pre> +</div> + +<p>Values are one of four types (which we list here mostly to call attention to the boolean format):</p> + +<ul> + <li>STRING, an arbitrary string (no spaces)</li> + <li>FLOAT, a floating-point value</li> + <li>INT, an integer</li> + <li> + <p>BOOLEAN, a boolean value. For booleans, <code class="highlighter-rouge">true</code> evaluates to true, and all other values evaluate +to false. For command-line options, the value may be omitted, in which case it evaluates to +true. For example, the following are equivalent:</p> + + <div class="highlighter-rouge"><pre class="highlight"><code>$JOSHUA/bin/decoder -mark-oovs true +$JOSHUA/bin/decoder -mark-oovs +</code></pre> + </div> + </li> +</ul> + +<h2 id="joshua-configuration-file">Joshua configuration file</h2> + +<p>In addition to the decoder parameters described below, the configuration file contains the model +feature weights. These weights are distinguished from runtime parameters in that they are delimited +by a space instead of an equals sign. They take the following +format, and by convention are placed at the end of the configuration file:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>lm_0 4.23 +tm_pt_0 -0.2 +OOVPenalty -100 +</code></pre> +</div> + +<p>Joshua can make use of thousands of features, which are described in further detail in the +<a href="features.html">feature file</a>.</p> + +<h2 id="joshua-decoder-parameters">Joshua decoder parameters</h2> + +<p>This section contains a list of the Joshua run-time parameters. An important note about the +parameters is that they are collapsed to canonical form, in which dashes (-) and underscores (-) are +removed and case is converted to lowercase. For example, the following parameter forms are +equivalent (either in the configuration file or from the command line):</p> + +<div class="highlighter-rouge"><pre class="highlight"><code><span class="p">{</span><span class="err">top-n,</span><span class="w"> </span><span class="err">topN,</span><span class="w"> </span><span class="err">top_n,</span><span class="w"> </span><span class="err">TOP_N,</span><span class="w"> </span><span class="err">t-o-p-N</span><span class="p">}</span><span class="w"> +</span><span class="p">{</span><span class="err">poplimit,</span><span class="w"> </span><span class="err">pop-limit,</span><span class="w"> </span><span class="err">pop-limit,</span><span class="w"> </span><span class="err">popLimit,PoPlImIt</span><span class="p">}</span><span class="w"> +</span></code></pre> +</div> + +<p>This basically defines equivalence classes of parameters, and relieves you of the task of having to +remember the exact format of each parameter.</p> + +<p>In what follows, we group the configuration parameters in the following groups:</p> + +<ul> + <li><a href="#general">General options</a></li> + <li><a href="#pruning">Pruning</a></li> + <li><a href="#tm">Translation model options</a></li> + <li><a href="#lm">Language model options</a></li> + <li><a href="#output">Output options</a></li> + <li><a href="#modes">Alternate modes of operation</a></li> +</ul> + +<p><a id="general"></a></p> + +<h3 id="general-decoder-options">General decoder options</h3> + +<ul> + <li> + <p><code class="highlighter-rouge">c</code>, <code class="highlighter-rouge">config</code> â <em>NULL</em></p> + + <p>Specifies the configuration file from which Joshua options are loaded. This feature is unique in + that it must be specified from the command line (obviously).</p> + </li> + <li> + <p><code class="highlighter-rouge">amortize</code> â <em>true</em></p> + + <p>When true, specifies that sorting of the rule lists at each trie node in the grammar should be +delayed until the trie node is accessed. When false, all such nodes are sorted before decoding +even begins. Setting to true results in slower per-sentence decoding, but allows the decoder to +begin translating almost immediately (especially with large grammars).</p> + </li> + <li> + <p><code class="highlighter-rouge">server-port</code> â <em>0</em></p> + + <p>If set to a nonzero value, Joshua will start a multithreaded TCP/IP server on the specified +port. Clients can connect to it directly through programming APIs or command-line tools like +<code class="highlighter-rouge">telnet</code> or <code class="highlighter-rouge">nc</code>.</p> + + <div class="highlighter-rouge"><pre class="highlight"><code>$ $JOSHUA/bin/decoder -m 30g -c /path/to/config/file -server-port 8723 +... +$ cat input.txt | nc localhost 8723 > results.txt +</code></pre> + </div> + </li> + <li> + <p><code class="highlighter-rouge">maxlen</code> â <em>200</em></p> + + <p>Input sentences longer than this are truncated.</p> + </li> + <li> + <p><code class="highlighter-rouge">feature-function</code></p> + + <p>Enables a particular feature function. See the <a href="features.html">feature function page</a> for more information.</p> + </li> + <li> + <p><code class="highlighter-rouge">oracle-file</code> â <em>NULL</em></p> + + <p>The location of a set of oracle reference translations, parallel to the input. When present, +after producing the hypergraph by decoding the input sentence, the oracle is used to rescore the +translation forest with a BLEU approximation in order to extract the oracle-translation from the +forest. This is useful for obtaining an (approximation to an) upper bound on your translation +model under particular search settings.</p> + </li> + <li> + <p><code class="highlighter-rouge">default-nonterminal</code> â <em>âXâ</em></p> + + <p>This is the nonterminal symbol assigned to out-of-vocabulary (OOV) items. Joshua assigns this + label to every word of the input, in fact, so that even known words can be translated as OOVs, if + the model prefers them. Usually, a very low weight on the <code class="highlighter-rouge">OOVPenalty</code> feature discourages their + use unless necessary.</p> + </li> + <li> + <p><code class="highlighter-rouge">goal-symbol</code> â <em>âGOALâ</em></p> + + <p>This is the symbol whose presence in the chart over the whole input span denotes a successful + parse (translation). It should match the LHS nonterminal in your glue grammar. Internally, + Joshua represents nonterminals enclosed in square brackets (e.g., â[GOAL]â), which you can + optionally supply in the configuration file.</p> + </li> + <li> + <p><code class="highlighter-rouge">true-oovs-only</code> â <em>false</em></p> + + <p>By default, Joshua creates an OOV entry for every word in the source sentence, regardless of +whether it is found in the grammar. This allows every word to be pushed through untranslated +(although potentially incurring a high cost based on the <code class="highlighter-rouge">OOVPenalty</code> feature). If this option is +set, then only true OOVs are entered into the chart as OOVs. To determine âtrueâ OOVs, Joshua +examines the first level of the grammar trie for each word of the input (this isnât a perfect +heuristic, since a word could be present only in deeper levels of the trie).</p> + </li> + <li> + <p><code class="highlighter-rouge">threads</code>, <code class="highlighter-rouge">num-parallel-decoders</code> â <em>1</em></p> + + <p>This determines how many simultaneous decoding threads to launch. </p> + + <p>Outputs are assembled in order and Joshua has to hold on to the complete target hypergraph until +it is ready to be processed for output, so too many simultaneous threads could result in lots of +memory usage if a long sentence results in many sentences being queued up. We have run Joshua +with as many as 64 threads without any problems of this kind, but itâs useful to keep in the back +of your mind.</p> + </li> + <li> + <p><code class="highlighter-rouge">weights-file</code> â NULL</p> + + <p>Weights are appended to the end of the Joshua configuration file, by convention. If you prefer to +put them in a separate file, you can do so, and point to the file with this parameter.</p> + </li> +</ul> + +<h3 id="pruning-options-a-idpruning-">Pruning options <a id="pruning"></a></h3> + +<ul> + <li> + <p><code class="highlighter-rouge">pop-limit</code> â <em>100</em></p> + + <p>The number of cube-pruning hypotheses that are popped from the candidates list for each span of +the input. Higher values result in a larger portion of the search space being explored at the +cost of an increased search time. For exhaustive search, set <code class="highlighter-rouge">pop-limit</code> to 0.</p> + </li> + <li> + <p><code class="highlighter-rouge">filter-grammar</code> â false</p> + + <p>Set to true, this enables dynamic sentence-level filtering. For each sentence, each grammar is +filtered at runtime down to rules that can be applied to the sentence under consideration. This +takes some time (which we havenât thoroughly quantified), but can result in the removal of many +rules that are only partially applicable to the sentence.</p> + </li> + <li><code class="highlighter-rouge">constrain-parse</code> â <em>false</em></li> + <li> + <p><code class="highlighter-rouge">use_pos_labels</code> â <em>false</em></p> + + <p><em>These features are not documented.</em></p> + </li> +</ul> + +<h3 id="translation-model-options-a-idtm-">Translation model options <a id="tm"></a></h3> + +<p>Joshua supports any number of translation models. Conventionally, two are supplied: the main grammar +containing translation rules, and the glue grammar for patching things together. Internally, Joshua +doesnât distinguish between the roles of these grammars; they are treated differently only in that +they typically have different span limits (the maximum input width they can be applied to).</p> + +<p>Grammars are instantiated with config file lines of the following form:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>tm = TYPE OWNER SPAN_LIMIT FILE +</code></pre> +</div> + +<ul> + <li><code class="highlighter-rouge">TYPE</code> is the grammar type, which must be set to âthraxâ. </li> + <li><code class="highlighter-rouge">OWNER</code> is the grammarâs owner, which defines the set of <a href="features.html">feature weights</a> that +apply to the weights found in each line of the grammar (using different owners allows each grammar +to have different sets and numbers of weights, while sharing owners allows weights to be shared +across grammars).</li> + <li><code class="highlighter-rouge">SPAN_LIMIT</code> is the maximum span of the input that rules from this grammar can be applied to. A +span limit of 0 means âno limitâ, while a span limit of -1 means that rules from this grammar must +be anchored to the left side of the sentence (index 0).</li> + <li><code class="highlighter-rouge">FILE</code> is the path to the file containing the grammar. If the file is a directory, it is assumed +to be <a href="packed.html">packed</a>. Only one packed grammar can currently be used at a time.</li> +</ul> + +<p>For reference, the following two translation model lines are used by the <a href="pipeline.html">pipeline</a>:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>tm = thrax pt 20 /path/to/packed/grammar +tm = thrax glue -1 /path/to/glue/grammar +</code></pre> +</div> + +<h3 id="language-model-options-a-idlm-">Language model options <a id="lm"></a></h3> + +<p>Joshua supports any number of language models. With Joshua 6.0, these +are just regular feature functions:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>feature-function = LanguageModel -lm_file /path/to/lm/file -lm_order N -lm_type TYPE +feature-function = StateMinimizingLanguageModel -lm_file /path/to/lm/file -lm_order N -lm_type TYPE +</code></pre> +</div> + +<p><code class="highlighter-rouge">LanguageModel</code> is a generic language model, supporting types âkenlmâ +(the default) and âberkeleylmâ. <code class="highlighter-rouge">StateMinimizingLanguageModel</code> +implements LM state minimization to reduce the size of context n-grams +where appropriate +(<a href="http://www.aclweb.org/anthology/W08-0402.pdf";>Li and Khudanpur, 2008</a>; +<a href="https://aclweb.org/anthology/N/N13/N13-1116.pdf";>Heafield et al., 2013</a>). This +is currently only supported by KenLM, so the <code class="highlighter-rouge">-lm_type</code> option is not +available here.</p> + +<p>The other key/value pairs are defined as follows:</p> + +<ul> + <li><code class="highlighter-rouge">lm_type</code>: one of âkenlmâ âberkeleylmâ</li> + <li><code class="highlighter-rouge">lm_order</code>: the order of the language model</li> + <li><code class="highlighter-rouge">lm_file</code>: the path to the language model file. All language model + types support the standard ARPA format. Additionally, if the LM + type is âkenlmâ, this file can be compiled into KenLMâs compiled + format (using the program at <code class="highlighter-rouge">$JOSHUA/bin/build_binary</code>); if the + the LM type is âberkeleylmâ, it can be compiled by following the + directions in + <code class="highlighter-rouge">$JOSHUA/src/joshua/decoder/ff/lm/berkeley_lm/README</code>. The + <a href="pipeline.html">pipeline</a> will automatically compile either type.</li> +</ul> + +<p>For each language model, you need to specify a feature weight in the following format:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>lm_0 WEIGHT +lm_1 WEIGHT +... +</code></pre> +</div> + +<p>where the indices correspond to the order of the language model declaration lines.</p> + +<h3 id="output-options-a-idoutput-">Output options <a id="output"></a></h3> + +<ul> + <li> + <p><code class="highlighter-rouge">output-format</code> <em>New in 5.0</em></p> + + <p>Joshua prints a lot of information to STDERR (making this more granular is on the TODO +list). Output to STDOUT is reserved for decoder translations, and is controlled by the</p> + + <ul> + <li> + <p><code class="highlighter-rouge">%i</code>: the sentence number (0-indexed)</p> + </li> + <li> + <p><code class="highlighter-rouge">%e</code>: the source sentence</p> + </li> + <li> + <p><code class="highlighter-rouge">%s</code>: the translated sentence</p> + </li> + <li> + <p><code class="highlighter-rouge">%S</code>: the translated sentence, with some basic capitalization and denomralization. e.g.,</p> + + <div class="highlighter-rouge"><pre class="highlight"><code>$ echo "¿ who you lookin' at , mr. ?" | $JOSHUA/bin/decoder -output-format "%S" -mark-oovs false 2> /dev/null +¿Who you lookin' at, Mr.? +</code></pre> + </div> + </li> + <li> + <p><code class="highlighter-rouge">%t</code>: the target-side tree projection, all printed on one line (PTB style)</p> + </li> + <li> + <p><code class="highlighter-rouge">%d</code>: the synchronous derivation, with each rules printed indented on their own lines</p> + </li> + <li> + <p><code class="highlighter-rouge">%f</code>: the list of feature values (as name=value pairs)</p> + </li> + <li> + <p><code class="highlighter-rouge">%c</code>: the model cost</p> + </li> + <li> + <p><code class="highlighter-rouge">%w</code>: the weight vector (unimplemented)</p> + </li> + <li> + <p><code class="highlighter-rouge">%a</code>: the alignments between source and target words (currently broken for hierarchical mode)</p> + </li> + </ul> + + <p>The default value is</p> + + <div class="highlighter-rouge"><pre class="highlight"><code>output-format = %i ||| %s ||| %f ||| %c +</code></pre> + </div> + + <p>i.e.,</p> + + <div class="highlighter-rouge"><pre class="highlight"><code>input ID ||| translation ||| model scores ||| score +</code></pre> + </div> + </li> + <li> + <p><code class="highlighter-rouge">top-n</code> â <em>300</em></p> + + <p>The number of translation hypotheses to output, sorted in decreasing order of model score</p> + </li> + <li> + <p><code class="highlighter-rouge">use-unique-nbest</code> â <em>true</em></p> + + <p>When constructing the n-best list for a sentence, skip hypotheses whose string has already been +output.</p> + </li> + <li> + <p><code class="highlighter-rouge">escape-trees</code> â <em>false</em></p> + </li> + <li> + <p><code class="highlighter-rouge">include-align-index</code> â <em>false</em></p> + + <p>Output the source words indices that each target word aligns to.</p> + </li> + <li> + <p><code class="highlighter-rouge">mark-oovs</code> â <em>false</em></p> + + <p>if <code class="highlighter-rouge">true</code>, this causes the text â_OOVâ to be appended to each untranslated word in the output.</p> + </li> + <li> + <p><code class="highlighter-rouge">visualize-hypergraph</code> â <em>false</em></p> + + <p>If set to true, a visualization of the hypergraph will be displayed, though you will have to +explicitly include the relevant jar files. See the example usage in +<code class="highlighter-rouge">$JOSHUA/examples/tree_visualizer/</code>, which contains a demonstration of a source sentence, +translation, and synchronous derivation.</p> + </li> + <li> + <p><code class="highlighter-rouge">dump-hypergraph</code> â ââ</p> + + <p>This feature directs that the hypergraph should be written to disk for each input sentence. If +set, the value should contain the string â%dâ, which is replaced with the sentence number. For +example,</p> + + <div class="highlighter-rouge"><pre class="highlight"><code>cat input.txt | $JOSHUA/bin/decoder -dump-hypergraph hgs/%d.txt +</code></pre> + </div> + + <p>Note that the output directory must exist.</p> + + <p>TODO: revive the +<a href="http://aclweb.org/aclwiki/index.php?title=Hypergraph_Format";>discussion on a common hypergraph format</a> +on the ACL Wiki and support that format.</p> + </li> +</ul> + +<h3 id="lattice-decoding">Lattice decoding</h3> + +<p>In addition to regular sentences, Joshua can decode weighted lattices encoded in +<a href="http://www.statmt.org/moses/?n=Moses.WordLattices";>the PLF format</a>, except that path costs should +be listed as <b>log probabilities</b> instead of probabilities. Lattice decoding was originally +added by Lane Schwartz and <a href="http://www.cs.cmu.edu/~cdyer/";>Chris Dyer</a>.</p> + +<p>Joshua will automatically detect whether the input sentence is a regular sentence (the usual case) +or a lattice. If a lattice, a feature will be activated that accumulates the cost of different +paths through the lattice. In this case, you need to ensure that a weight for this feature is +present in <a href="decoder.html">your model file</a>. The <a href="pipeline.html">pipeline</a> will handle this +automatically, or if you are doing this manually, you can add the line</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>SourcePath COST +</code></pre> +</div> + +<p>to your Joshua configuration file. </p> + +<p>Lattices must be listed one per line.</p> + +<h3 id="alternate-modes-of-operation-a-idmodes-">Alternate modes of operation <a id="modes"></a></h3> + +<p>In addition to decoding input sentences in the standard way, Joshua supports both <em>constrained +decoding</em> and <em>synchronous parsing</em>. In both settings, both the source and target sides are provided +as input, and the decoder finds a derivation between them.</p> + +<h4 id="constrained-decoding">Constrained decoding</h4> + +<p>To enable constrained decoding, simply append the desired target string as part of the input, in +the following format:</p> + +<div class="highlighter-rouge"><pre class="highlight"><code>source sentence ||| target sentence +</code></pre> +</div> + +<p>Joshua will translate the source sentence constrained to the target sentence. There are a few +caveats:</p> + +<ul> + <li> + <p>Left-state minimization cannot be enabled for the language model</p> + </li> + <li> + <p>A heuristic is used to constrain the derivation (the LM state must match against the +input). This is not a perfect heuristic, and sometimes results in analyses that are not +perfectly constrained to the input, but have extra words.</p> + </li> +</ul> + +<h4 id="synchronous-parsing">Synchronous parsing</h4> + +<p>Joshua supports synchronous parsing as a two-step sequence of monolingual parses, as described in +Dyer (NAACL 2010) (<a href="http://www.aclweb.org/anthology/N10-1033â.pdf";>PDF</a>). To enable this:</p> + +<ul> + <li> + <p>Set the configuration parameter <code class="highlighter-rouge">parse = true</code>.</p> + </li> + <li> + <p>Remove all language models from the input file </p> + </li> + <li> + <p>Provide input in the following format:</p> + + <div class="highlighter-rouge"><pre class="highlight"><code> source sentence ||| target sentence +</code></pre> + </div> + </li> +</ul> + +<p>You may also wish to display the synchronouse parse tree (<code class="highlighter-rouge">-output-format %t</code>) and the alignment +(<code class="highlighter-rouge">-show-align-index</code>).</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/53cc3005/6.0/decoder.md ---------------------------------------------------------------------- diff --git a/6.0/decoder.md b/6.0/decoder.md deleted file mode 100644 index e8dc8c9..0000000 --- a/6.0/decoder.md +++ /dev/null @@ -1,385 +0,0 @@ ---- -layout: default6 -category: links -title: Decoder configuration parameters ---- - -Joshua configuration parameters affect the runtime behavior of the decoder itself. This page -describes the complete list of these parameters and describes how to invoke the decoder manually. - -To run the decoder, a convenience script is provided that loads the necessary Java libraries. -Assuming you have set the environment variable `$JOSHUA` to point to the root of your installation, -its syntax is: - - $JOSHUA/bin/decoder [-m memory-amount] [-c config-file other-joshua-options ...] - -The `-m` argument, if present, must come first, and the memory specification is in Java format -(e.g., 400m, 4g, 50g). Most notably, the suffixes "m" and "g" are used for "megabytes" and -"gigabytes", and there cannot be a space between the number and the unit. The value of this -argument is passed to Java itself in the invocation of the decoder, and the remaining options are -passed to Joshua. The `-c` parameter has special import because it specifies the location of the -configuration file. - -The Joshua decoder works by reading from STDIN and printing translations to STDOUT as they are -received, according to a number of [output options](#output). If no run-time parameters are -specified (e.g., no translation model), sentences are simply pushed through untranslated. Blank -lines are similarly pushed through as blank lines, so as to maintain parallelism with the input. - -Parameters can be provided to Joshua via a configuration file and from the command -line. Command-line arguments override values found in the configuration file. The format for -configuration file parameters is - - parameter = value - -Command-line options are specified in the following format - - -parameter value - -Values are one of four types (which we list here mostly to call attention to the boolean format): - -- STRING, an arbitrary string (no spaces) -- FLOAT, a floating-point value -- INT, an integer -- BOOLEAN, a boolean value. For booleans, `true` evaluates to true, and all other values evaluate - to false. For command-line options, the value may be omitted, in which case it evaluates to - true. For example, the following are equivalent: - - $JOSHUA/bin/decoder -mark-oovs true - $JOSHUA/bin/decoder -mark-oovs - -## Joshua configuration file - -In addition to the decoder parameters described below, the configuration file contains the model -feature weights. These weights are distinguished from runtime parameters in that they are delimited -by a space instead of an equals sign. They take the following -format, and by convention are placed at the end of the configuration file: - - lm_0 4.23 - tm_pt_0 -0.2 - OOVPenalty -100 - -Joshua can make use of thousands of features, which are described in further detail in the -[feature file](features.html). - -## Joshua decoder parameters - -This section contains a list of the Joshua run-time parameters. An important note about the -parameters is that they are collapsed to canonical form, in which dashes (-) and underscores (-) are -removed and case is converted to lowercase. For example, the following parameter forms are -equivalent (either in the configuration file or from the command line): - - {top-n, topN, top_n, TOP_N, t-o-p-N} - {poplimit, pop-limit, pop-limit, popLimit,PoPlImIt} - -This basically defines equivalence classes of parameters, and relieves you of the task of having to -remember the exact format of each parameter. - -In what follows, we group the configuration parameters in the following groups: - -- [General options](#general) -- [Pruning](#pruning) -- [Translation model options](#tm) -- [Language model options](#lm) -- [Output options](#output) -- [Alternate modes of operation](#modes) - -<a id="general" /> - -### General decoder options - -- `c`, `config` --- *NULL* - - Specifies the configuration file from which Joshua options are loaded. This feature is unique in - that it must be specified from the command line (obviously). - -- `amortize` --- *true* - - When true, specifies that sorting of the rule lists at each trie node in the grammar should be - delayed until the trie node is accessed. When false, all such nodes are sorted before decoding - even begins. Setting to true results in slower per-sentence decoding, but allows the decoder to - begin translating almost immediately (especially with large grammars). - -- `server-port` --- *0* - - If set to a nonzero value, Joshua will start a multithreaded TCP/IP server on the specified - port. Clients can connect to it directly through programming APIs or command-line tools like - `telnet` or `nc`. - - $ $JOSHUA/bin/decoder -m 30g -c /path/to/config/file -server-port 8723 - ... - $ cat input.txt | nc localhost 8723 > results.txt - -- `maxlen` --- *200* - - Input sentences longer than this are truncated. - -- `feature-function` - - Enables a particular feature function. See the [feature function page](features.html) for more information. - -- `oracle-file` --- *NULL* - - The location of a set of oracle reference translations, parallel to the input. When present, - after producing the hypergraph by decoding the input sentence, the oracle is used to rescore the - translation forest with a BLEU approximation in order to extract the oracle-translation from the - forest. This is useful for obtaining an (approximation to an) upper bound on your translation - model under particular search settings. - -- `default-nonterminal` --- *"X"* - - This is the nonterminal symbol assigned to out-of-vocabulary (OOV) items. Joshua assigns this - label to every word of the input, in fact, so that even known words can be translated as OOVs, if - the model prefers them. Usually, a very low weight on the `OOVPenalty` feature discourages their - use unless necessary. - -- `goal-symbol` --- *"GOAL"* - - This is the symbol whose presence in the chart over the whole input span denotes a successful - parse (translation). It should match the LHS nonterminal in your glue grammar. Internally, - Joshua represents nonterminals enclosed in square brackets (e.g., "[GOAL]"), which you can - optionally supply in the configuration file. - -- `true-oovs-only` --- *false* - - By default, Joshua creates an OOV entry for every word in the source sentence, regardless of - whether it is found in the grammar. This allows every word to be pushed through untranslated - (although potentially incurring a high cost based on the `OOVPenalty` feature). If this option is - set, then only true OOVs are entered into the chart as OOVs. To determine "true" OOVs, Joshua - examines the first level of the grammar trie for each word of the input (this isn't a perfect - heuristic, since a word could be present only in deeper levels of the trie). - -- `threads`, `num-parallel-decoders` --- *1* - - This determines how many simultaneous decoding threads to launch. - - Outputs are assembled in order and Joshua has to hold on to the complete target hypergraph until - it is ready to be processed for output, so too many simultaneous threads could result in lots of - memory usage if a long sentence results in many sentences being queued up. We have run Joshua - with as many as 64 threads without any problems of this kind, but it's useful to keep in the back - of your mind. - -- `weights-file` --- NULL - - Weights are appended to the end of the Joshua configuration file, by convention. If you prefer to - put them in a separate file, you can do so, and point to the file with this parameter. - -### Pruning options <a id="pruning" /> - -- `pop-limit` --- *100* - - The number of cube-pruning hypotheses that are popped from the candidates list for each span of - the input. Higher values result in a larger portion of the search space being explored at the - cost of an increased search time. For exhaustive search, set `pop-limit` to 0. - -- `filter-grammar` --- false - - Set to true, this enables dynamic sentence-level filtering. For each sentence, each grammar is - filtered at runtime down to rules that can be applied to the sentence under consideration. This - takes some time (which we haven't thoroughly quantified), but can result in the removal of many - rules that are only partially applicable to the sentence. - -- `constrain-parse` --- *false* -- `use_pos_labels` --- *false* - - *These features are not documented.* - -### Translation model options <a id="tm" /> - -Joshua supports any number of translation models. Conventionally, two are supplied: the main grammar -containing translation rules, and the glue grammar for patching things together. Internally, Joshua -doesn't distinguish between the roles of these grammars; they are treated differently only in that -they typically have different span limits (the maximum input width they can be applied to). - -Grammars are instantiated with config file lines of the following form: - - tm = TYPE OWNER SPAN_LIMIT FILE - -* `TYPE` is the grammar type, which must be set to "thrax". -* `OWNER` is the grammar's owner, which defines the set of [feature weights](features.html) that - apply to the weights found in each line of the grammar (using different owners allows each grammar - to have different sets and numbers of weights, while sharing owners allows weights to be shared - across grammars). -* `SPAN_LIMIT` is the maximum span of the input that rules from this grammar can be applied to. A - span limit of 0 means "no limit", while a span limit of -1 means that rules from this grammar must - be anchored to the left side of the sentence (index 0). -* `FILE` is the path to the file containing the grammar. If the file is a directory, it is assumed - to be [packed](packed.html). Only one packed grammar can currently be used at a time. - -For reference, the following two translation model lines are used by the [pipeline](pipeline.html): - - tm = thrax pt 20 /path/to/packed/grammar - tm = thrax glue -1 /path/to/glue/grammar - -### Language model options <a id="lm" /> - -Joshua supports any number of language models. With Joshua 6.0, these -are just regular feature functions: - - feature-function = LanguageModel -lm_file /path/to/lm/file -lm_order N -lm_type TYPE - feature-function = StateMinimizingLanguageModel -lm_file /path/to/lm/file -lm_order N -lm_type TYPE - -`LanguageModel` is a generic language model, supporting types 'kenlm' -(the default) and 'berkeleylm'. `StateMinimizingLanguageModel` -implements LM state minimization to reduce the size of context n-grams -where appropriate -([Li and Khudanpur, 2008](http://www.aclweb.org/anthology/W08-0402.pdf); -[Heafield et al., 2013](https://aclweb.org/anthology/N/N13/N13-1116.pdf)). This -is currently only supported by KenLM, so the `-lm_type` option is not -available here. - -The other key/value pairs are defined as follows: - -* `lm_type`: one of "kenlm" "berkeleylm" -* `lm_order`: the order of the language model -* `lm_file`: the path to the language model file. All language model - types support the standard ARPA format. Additionally, if the LM - type is "kenlm", this file can be compiled into KenLM's compiled - format (using the program at `$JOSHUA/bin/build_binary`); if the - the LM type is "berkeleylm", it can be compiled by following the - directions in - `$JOSHUA/src/joshua/decoder/ff/lm/berkeley_lm/README`. The - [pipeline](pipeline.html) will automatically compile either type. - -For each language model, you need to specify a feature weight in the following format: - - lm_0 WEIGHT - lm_1 WEIGHT - ... - -where the indices correspond to the order of the language model declaration lines. - -### Output options <a id="output" /> - -- `output-format` *New in 5.0* - - Joshua prints a lot of information to STDERR (making this more granular is on the TODO - list). Output to STDOUT is reserved for decoder translations, and is controlled by the - - - `%i`: the sentence number (0-indexed) - - - `%e`: the source sentence - - - `%s`: the translated sentence - - - `%S`: the translated sentence, with some basic capitalization and denomralization. e.g., - - $ echo "¿ who you lookin' at , mr. ?" | $JOSHUA/bin/decoder -output-format "%S" -mark-oovs false 2> /dev/null - ¿Who you lookin' at, Mr.? - - - `%t`: the target-side tree projection, all printed on one line (PTB style) - - - `%d`: the synchronous derivation, with each rules printed indented on their own lines - - - `%f`: the list of feature values (as name=value pairs) - - - `%c`: the model cost - - - `%w`: the weight vector (unimplemented) - - - `%a`: the alignments between source and target words (currently broken for hierarchical mode) - - The default value is - - output-format = %i ||| %s ||| %f ||| %c - - i.e., - - input ID ||| translation ||| model scores ||| score - -- `top-n` --- *300* - - The number of translation hypotheses to output, sorted in decreasing order of model score - -- `use-unique-nbest` --- *true* - - When constructing the n-best list for a sentence, skip hypotheses whose string has already been - output. - -- `escape-trees` --- *false* - -- `include-align-index` --- *false* - - Output the source words indices that each target word aligns to. - -- `mark-oovs` --- *false* - - if `true`, this causes the text "_OOV" to be appended to each untranslated word in the output. - -- `visualize-hypergraph` --- *false* - - If set to true, a visualization of the hypergraph will be displayed, though you will have to - explicitly include the relevant jar files. See the example usage in - `$JOSHUA/examples/tree_visualizer/`, which contains a demonstration of a source sentence, - translation, and synchronous derivation. - -- `dump-hypergraph` --- "" - - This feature directs that the hypergraph should be written to disk for each input sentence. If - set, the value should contain the string "%d", which is replaced with the sentence number. For - example, - - cat input.txt | $JOSHUA/bin/decoder -dump-hypergraph hgs/%d.txt - - Note that the output directory must exist. - - TODO: revive the - [discussion on a common hypergraph format](http://aclweb.org/aclwiki/index.php?title=Hypergraph_Format) - on the ACL Wiki and support that format. - -### Lattice decoding - -In addition to regular sentences, Joshua can decode weighted lattices encoded in -[the PLF format](http://www.statmt.org/moses/?n=Moses.WordLattices), except that path costs should -be listed as <b>log probabilities</b> instead of probabilities. Lattice decoding was originally -added by Lane Schwartz and [Chris Dyer](http://www.cs.cmu.edu/~cdyer/). - -Joshua will automatically detect whether the input sentence is a regular sentence (the usual case) -or a lattice. If a lattice, a feature will be activated that accumulates the cost of different -paths through the lattice. In this case, you need to ensure that a weight for this feature is -present in [your model file](decoder.html). The [pipeline](pipeline.html) will handle this -automatically, or if you are doing this manually, you can add the line - - SourcePath COST - -to your Joshua configuration file. - -Lattices must be listed one per line. - -### Alternate modes of operation <a id="modes" /> - -In addition to decoding input sentences in the standard way, Joshua supports both *constrained -decoding* and *synchronous parsing*. In both settings, both the source and target sides are provided -as input, and the decoder finds a derivation between them. - -#### Constrained decoding - -To enable constrained decoding, simply append the desired target string as part of the input, in -the following format: - - source sentence ||| target sentence - -Joshua will translate the source sentence constrained to the target sentence. There are a few -caveats: - - * Left-state minimization cannot be enabled for the language model - - * A heuristic is used to constrain the derivation (the LM state must match against the - input). This is not a perfect heuristic, and sometimes results in analyses that are not - perfectly constrained to the input, but have extra words. - -#### Synchronous parsing - -Joshua supports synchronous parsing as a two-step sequence of monolingual parses, as described in -Dyer (NAACL 2010) ([PDF](http://www.aclweb.org/anthology/N10-1033â.pdf)). To enable this: - - - Set the configuration parameter `parse = true`. - - - Remove all language models from the input file - - - Provide input in the following format: - - source sentence ||| target sentence - -You may also wish to display the synchronouse parse tree (`-output-format %t`) and the alignment -(`-show-align-index`). -
