Kārlis & Christian, I have downloaded and compiled your lattice MERT. I am interested in giving it a try, and would be grateful for any assistance you might be able to provide in setting it up.
Would you mind sending me a copy of your modified mert-moses.pl that calls latticemert? Thanks, Lane Schwartz On Mon, Mar 28, 2011 at 4:48 AM, Kārlis Goba <[email protected]> wrote: > The project lives its happy quiet life separately from Moses in github > (https://github.com/christianbuck/Moses-Lattice-MERT). > > It is in a usable state, however, lacks our commitment to make a proper > documentation and to integrate it properly with the newest Moses MERT scripts. > > I am using it with a separate script derived from mert-moses.pl some time > ago. It supports only BLEU scoring, and is quite slow on large search graphs. > The convergence seems to work better than n-best MERT. If you are interested, > I can help you with setting it up. > > I do keep this project in front of my eyes. Maybe it takes another MT > marathon to make the last 100 metres. Several optimizations and improvements > are on my list. > > Regards, > Kārlis > >> -----Original Message----- >> From: [email protected] [mailto:moses-support- >> [email protected]] On Behalf Of Philipp Koehn >> Sent: Friday, March 25, 2011 9:20 PM >> To: Lane Schwartz >> Cc: [email protected]; Christian Buck >> Subject: Re: [Moses-support] Implementation of Lattice MERT >> >> Hi, >> >> Christian Buck was involved in implemented it, but it was never >> properly >> integrated into Moses. Maybe he can share some light on this, and it >> may actually already work. >> >> -phi >> >> On Fri, Mar 25, 2011 at 6:59 PM, Lane Schwartz <[email protected]> >> wrote: >> > Does anyone know if there's an open implementation of Lattice MERT >> > (Macherey, et al, 2008)? Strangely, the authors seem to have >> forgotten to >> > include the URL to download their implementation. :) >> > >> > Just to be clear, I don't mean running MERT where you give Moses a >> > source-language lattice to decode. >> > >> > Cheers, >> > Lane >> > >> > _______________________________________________ >> > Moses-support mailing list >> > [email protected] >> > http://mailman.mit.edu/mailman/listinfo/moses-support >> > >> > >> _______________________________________________ >> Moses-support mailing list >> [email protected] >> http://mailman.mit.edu/mailman/listinfo/moses-support -- When a place gets crowded enough to require ID's, social collapse is not far away. It is time to go elsewhere. The best thing about space travel is that it made it possible to go elsewhere. -- R.A. Heinlein, "Time Enough For Love" _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
