cunei machine translation platform
documentation
To get you started with Cunei we will build a small French-English system trained on the freely-available Europarl corpus. More information on the Europarl corpus is available at http://statmt.org/europarl/.
Prerequisites
Please download and install the software listed above. For this tutorial, we will assume Java, Subversion, and Apache Ant are included in your $PATH. Set the environment variables below to the location of your GIZA++ and SRILM installations.
export GIZA_HOME=/path/to/GIZA++-v2/
export SRILM_HOME=/path/to/srilm/
Install Cunei
The source code for Cunei is hosted in a Subversion repository. Run the following command to check out the latest version of of Cunei into the directory cunei.
svn co -r801 https://svn.cunei.org/svnroot/cunei /path/to/cunei
Throughout this tutorial we will run commands and reference files relative to Cunei's base directory. Please change your working directory now.
cd /path/to/cunei/
Build a System
The build process is now completely automated. Just type the command below to generate a example French-English system.
ant -Dcunei.mem=4g -f data/systems/fr-en.default/build.xml system
This will take a long time to complete, but the process should end with a BUILD SUCCESSFUL message. If instead you are presented with an error, please email a description of the problem to cunei-support@lists.sourceforge.net.

To better understand the steps involved in building a system it may be helpful to reference the old step-by-step tutorial.

Translate
You should have a working system that can produce translations--let's give it a whirl!

To verify that everything is working, generate the translation lattice with the command below. This will output the many possible translations found for each word or phrase in the test sentence.

echo "Je voudrais une bouteille d'eau" | \ bin/cunei.sh Translate data/systems/fr-en.default/config.base
Now try generating full-sentence translations with the command below. This will output the top four translations of the sentence.
echo "Je voudrais une bouteille d'eau" | \ bin/cunei.sh Decode data/systems/fr-en.default/config.base \ -XDecoder.N-Best 4
Optimize
The default parameters are not adjusted for any particular language pair and, thus, are quite poor. Now it's time to remedy that. The following command will optimize Cunei's settings and significantly improve the quality of translations. A test document will be translated over and over, each time adjusting Cunei's parameters in order to produce translations that (as closely as possible) match a human translated document. This process will use a lot of memory and may take a few days to complete.
ant -Dcunei.mem=4g -f data/systems/fr-en.default/build.xml opt
When optimization is complete a new configuration file will be created for you with the optimized parameters. From now on, use this new configuration file located at data/systems/fr-en.default/config.base.r801.0.opt for translation.
Workbench
More information coming soon...

Congratulations
Congratulations on completing the Cunei tutorial. Feedback is welcome. If something didn't quite work right or you have suggestions for improvement please send mail to cunei-support@lists.sourceforge.net.

Happy translating!