Skip to content
This repository has been archived by the owner. It is now read-only.
Permalink
Browse files
Fixed redirect and download message
  • Loading branch information
mjpost committed May 20, 2015
1 parent 9c64de0 commit 29556b18c016261e20041f42013c038d1cfcc1b9
Show file tree
Hide file tree
Showing 4 changed files with 14 additions and 20 deletions.
@@ -26,10 +26,11 @@ To facilitate these tasks, the pipeline script:
- Allows you to jump into and out of the pipeline at a set of predefined places (e.g., the alignment
stage), so long as you provide the missing dependencies.

The Joshua pipeline script is designed in the spirit of Moses' `train-model.pl`, and shares many of
its features. It is not as extensive, however, as Moses'
The Joshua pipeline script is designed in the spirit of Moses' `train-model.pl`, and shares
(and has borrowed) many of its features. It is not as extensive as Moses'
[Experiment Management System](http://www.statmt.org/moses/?n=FactoredTraining.EMS), which allows
the user to define arbitrary execution dependency graphs.
the user to define arbitrary execution dependency graphs. However, it is significantly simpler to
use, allowing many systems to be built with a single command (that may run for days or weeks).

## Installation

@@ -65,10 +66,11 @@ external packages, some of which are included with Joshua.

- [SRILM](http://www.speech.sri.com/projects/srilm/) (not included)

By default, the pipeline uses a Java program from the
[Berkeley LM](http://code.google.com/p/berkeleylm/) package that constructs an
Kneser-Ney-smoothed language model in ARPA format from the target side of your training data. If
you wish to use SRILM instead, you need to do the following:
By default, the pipeline uses the included [KenLM](https://kheafield.com/code/kenlm/) for
building (and also querying) language models. Joshua also includes a Java program from the
[Berkeley LM](http://code.google.com/p/berkeleylm/) package that contains code for constructing a
Kneser-Ney-smoothed language model in ARPA format from the target side of your training data.
There is no need to use SRILM, but if you do wish to use it, you need to do the following:

1. Install SRILM and set the `$SRILM` environment variable to point to its installed location.
1. Add the `--lm-gen srilm` flag to your pipeline invocation.
@@ -89,7 +91,7 @@ intermediate files in the *run directory*. By default, the run directory is the
but it can be changed with the `--rundir` parameter.

For this quick start, we will be working with the example that can be found in
`$JOSHUA/examples/pipeline`. This example contains 1,000 sentences of Urdu-English data (the full
`$JOSHUA/examples/training`. This example contains 1,000 sentences of Urdu-English data (the full
dataset is available as part of the
[Indian languages parallel corpora](/indian-parallel-corpora/) with
100-sentence tuning and test sets with four references each.
@@ -2,15 +2,6 @@
<html lang="en-US">
<head>
<meta charset="UTF-8">
<meta http-equiv="refresh" content="1;url=http://example.com">
<script type="text/javascript">
window.location.href = "http://cs.jhu.edu/~post/files/joshua-v6.0.2.tgz"
</script>
<title>Page Redirection</title>
<meta http-equiv="refresh" content="1;url=http://cs.jhu.edu/~post/files/joshua-v6.0.2.tgz" />
</head>
<body>
If you are not redirected automatically, follow
<a href='http://cs.jhu.edu/~post/files/joshua-v6.0.2.tgz'>this link</a>
to download Joshua directly.
</body>
</html>
@@ -3,8 +3,8 @@
title: Joshua releases
---

The current release of Joshua is version 6.0.1, which can be [downloaded
here](6.0/). It was released on March 6, 2015.
The current release of Joshua is version 6.0.2, which can be [downloaded
here](6.0/). It was released on April 10, 2015.

Older versions are also available:

0 comments on commit 29556b1

Please sign in to comment.