The output word graph is in HTK Standard Lattice Format (SLF).  A
number of tools (for example, SRILM's lattice-tool) read word graphs
in this format and can do things with it.  You ought to be able to
find the path in the lattice corresponding to the decoder's best path.

Chris

On Sun, Aug 23, 2009 at 4:12 PM, Mostafa
Aghajani<[email protected]> wrote:
> Hi,
>
> I have used moses to generate a word graph (with –owg parameter) and here
> are some lines of the result:
>
>
>
> J=0         S=0         E=164    a=-0.149143, -0.0213871, -0.106304,
> -0.0113856, 0.999896              l=-6.31889           r=-50, 0, -0.855577,
> 0, 0, 0    w=.
>
> J=1         S=0         E=72      a=-4.65502, -4.93344, -5.12308, -4.84343,
> 0.999896            l=-8.26024           r=-10, 0, -1.49066, 0, 0,
> 0                w='s
>
> J=2         S=0         E=172    a=-6.19471, -5.827, -6.24869, -5.79268,
> 0.999896 l=-6.13104           r=-50, 0, -0.52219, 0, 0, 0               w=,
>
> J=3         S=0         E=171    a=-2.49257, -2.43084, -6.54021, -6.29025,
> 0.999896            l=-8.62969           r=-50, 0, -0.747215, 0, 0,
> 0                w=;
>
> J=4         S=0         E=150    a=-2.85263, -2.84781, -2.99573, -2.83321,
> 0.999896            l=-11.8768           r=-40, 0, -1.09861, 0, 0,
> 0                w=homes
>
> J=5         S=0         E=148    a=-0.693147, -0.878071, -0.660357,
> -0.753772, 0.999896   l=-11.8506           r=-40, 0, -1.97716, 0, 0,
> 0                w=house
>
> J=6         S=0         E=152    a=-3.3322, -3.3322, -4.09434, -4.21951,
> 0.999896 l=-12.3013           r=-40, 0, -1.60944, 0, 0, 0
> w=household
>
> J=7         S=0         E=142    a=-1.09861, -1.09861, -4.04305, -4.29046,
> 0.999896            l=-15.0424           r=-30, 0, -0.510826, 0, 0,
> 0                w=painted
>
> J=8         S=0         E=141    a=-1.60944, -2.19723, -4.04305, -4.29046,
> 0.999896            l=-13.9805           r=-30, 0, -0.510826, 0, 0,
> 0                w=small-scale
>
> J=9         S=0         E=137    a=-1.99243, -2.16905, -2.94444, -2.90417,
> 0.999896            l=-12.5811           r=-30, 0, -2.19723, 0, 0,
> 0                w=tiny
>
> J=10       S=0         E=80      a=-3.04452, -0.734794, -7.72577, -5.4807,
> 0.999896            l=-10.0289           r=-10, 0, -0.20067, 0, 0,
> 0                w=" is
>
>
>
> My question is how can I rebuild the word graph using these data?
>
> For example in line 1, is S=0 means that this a start node and  E=164 means
> that it connects to a node with S=164? If this is the answer (my guess), why
> I can’t create the moses output translation (this is a small house.) using
> this word graph?
>
>
>
> Best regards,
>
> M.Aghajani
>
> _______________________________________________
> 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

Reply via email to