Hi All
There's been an enormous number of changes in Moses in the last month.
1. Synchronous CFG based decoding, a la Hiero (Chiang 2005), plus
with syntax. And all the scripts to go with it. (Thanks to Philip
Williams and Hieu Hoang)
2. caching clearing in IRST LM (Nicola Bertoldi)
3. Factored Language Model. (Ondrej Bojar)
4. Fixes to lattice (Christian Hardmeier, Arianna Bisazza, Suzy Howlett)
5. zmert (Ondrej Bojar)
6. Suffix arrays (Abby Levenberg)
7. Lattice MBR and consensus decoding (Barry Haddow & Abhishek Arun)
8. Simple program that illustrates how to access a phrase table on
disk from an external program (Felipe Sánchez-Martínez)
9. Odds and sods by Raphael Payen and Sara Stymne.
The biggest change has been the extension of the phrase-based framework
to chart decoding. This has touched most parts of the toolkit.
Therefore, if you download the update, please also use the updated
training and tuning scripts that go with it. We have some explanation of
how it works at
http://www.statmt.org/moses/?n=Moses.SyntaxTutorial
More details will come in the following weeks and months.
The old code has been tagged for prosperity in the sourceforge svn
tags/LAST-PHRASE-BASED-ONLY-2010-04-08
The new code is in svn trunk and via download
http://sourceforge.net/projects/mosesdecoder/files/mosesdecoder/2010-04-26/moses-2010-04-26.tgz/download
I hope you'll find useful. Fingers crossed!
Hieu
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
