Re: [Moses-support] Fwd: Re: Major bug found in Moses

2015-06-17 Thread liling tan
Dear James and Moses devs, I guess everyone's hunch would be whether you've done tuning correctly before the awkward results you've reported. Read on for sob story about me and moses and some guide to sooth the tone, try i may. Please skip/delete, if you would not like to read the sob stor

Re: [Moses-support] Fwd: Re: Major bug found in Moses

2015-06-17 Thread Read, James C
So can we agree that this is undesirable behaviour and therefore a bug? James From: moses-support-boun...@mit.edu on behalf of Marcin Junczys-Dowmunt Sent: Wednesday, June 17, 2015 5:04 PM To: Moses Support Subject: [Moses-support] Fwd: Re: Major bug found in

[Moses-support] Fwd: Re: Major bug found in Moses

2015-06-17 Thread Marcin Junczys-Dowmunt
As I said. With an unpruned phrase table and an decoder that just optmizes some unreasonble set of weights all bets are off, so if you get very low BLEU point there, it's not surprising. It's probably jumping around in a very weird search space. With a pruned phrase table you restrict the search