yep, you're right. I fixed the decoder to output this for confusion network
input:
...
PhraseModel I 0.50
PhraseModel tm 0.20
PhraseModel tm 0.20
PhraseModel tm 0.20
PhraseModel tm 0.20
PhraseModel tm 0.20
https://github.com/moses-smt/mosesdecoder/commit/44a0e
> On 02/04/2013 20:42, Rob Voigt wrote:
> > Hi all,
> >
> > I'm trying to use confusion networks with Moses - I can decode with them
successfully, manually inputting
> an insertion weight (-weight-i), but am running into trouble doing MERT on
a model that uses confusion networks.
> >
> > Running
gt; From: "Hieu Hoang"
> To: "Rob Voigt"
> Sent: Thursday, April 4, 2013 5:21:42 AM
> Subject: Re: [Moses-support] Running MERT with confusion network input
>
>
> I'll take a look at it over the next few days. The confusion network isn't
> often
Hi Rob
I haven't used confusion network input but I do know about the
implementation of the input weights (it's added as an extra weight to
the weight table).
If you can't figure out how to fix it, please send me a small sample
model to replicate the problem and I'll take a look at it.
On 02/
Hi all,
I'm trying to use confusion networks with Moses - I can decode with them
successfully, manually inputting an insertion weight (-weight-i), but am
running into trouble doing MERT on a model that uses confusion networks.
Running this command, with weight-i specified in the moses.ini file
