Re: [Moses-support] tree-to-string training

Hieu Hoang Sun, 23 Oct 2011 23:47:31 -0700

hi graham,

everything seems to be ok with the decoding. The decoding is using rulesother than glue rules. For instance, the range [3..6] is translated by arule from your translation table.

However, it is true that no consecutive rules are joined by anythingother than the glue rule. That's often the case with syntax decoding.Also, you've specified

   --NonTermConsecSource
so you'll never get a rule like
   VP --> [VB,1] [NP,2] #   X --> [X,1] [X,2]

I think the argument is unnecessary for tree-to-string decoding andlimits some good translation rules that may be extracted.

Also, the decoding algorithm in Moses separates the constraint ofmatching the non-terminal labels between the translation rule and theinput parse, and the translation rule and it's child hypothesis.

The tree-to-string as you have it only matches the non-term of the ruleand the input parse, the 'target' non-terminals are always X.

The trace file only shows the non-terminal label of the 'target' side soyou don't see the source non-term.


not sure if that makes sense

On 23/10/2011 12:18, Graham Neubig wrote:

Hi,

I'm trying to train a tree-to-string model and have gotten gotten
train-model.perl to run properly, but it seems that when I perform
decoding the decoder is using nothing but the glue rules. My
train-model.perl command is as follows:

$SCRIPTS_ROOTDIR/training/train-model.perl -scripts-root-dir
$SCRIPTS_ROOTDIR -root-dir work -corpus moses-0128.ja-en -f en -e ja
-alignment grow-diag-final-and -lm 0:3:`pwd`/ja-ja.arpa -source-syntax
-glue-grammar -extract-options "--MinWords 0 --MinHoleSource 1
--MinWords 0 --NonTermConsecSource"&>  err.txt

Using this model, a decoded looks like this in Moses's output and the
trace file:

Translating:<s>  he revolutionized the japanese ink painting .</s>
||| [0,0]=X (1) [0,1]=X (1) [0,2]=X (1) [0,3]=X (1) [0,4]=X (1)
[0,5]=X (1) [0,6]=X (1) [0,7]=X (1) [0,8]=X (1) [1,1]=X (1) [1,1]=NP
(1) [1,1]=PRP (1) [1,2]=X (1) [1,3]=X (1) [1,4]=X (1) [1,5]=X (1)
[1,6]=X (1) [1,7]=X (1) [1,7]=S (1) [1,8]=X (1) [2,2]=X (1) [2,2]=VBD
(1) [2,3]=X (1) [2,4]=X (1) [2,5]=X (1) [2,6]=X (1) [2,6]=VP (1)
[2,7]=X (1) [2,8]=X (1) [3,3]=X (1) [3,3]=DT (1) [3,4]=X (1) [3,5]=X
(1) [3,6]=X (1) [3,6]=NP (1) [3,7]=X (1) [3,8]=X (1) [4,4]=X (1)
[4,4]=JJ (1) [4,5]=X (1) [4,6]=X (1) [4,7]=X (1) [4,8]=X (1) [5,5]=X
(1) [5,5]=NN (1) [5,6]=X (1) [5,7]=X (1) [5,8]=X (1) [6,6]=X (1)
[6,6]=NN (1) [6,7]=X (1) [6,8]=X (1) [7,7]=X (1) [7,7]=. (1) [7,8]=X
(1) [8,8]=X (1)

Num of hypo = 10065 --- cells:
  0   1   2   3   4   5   6   7   8
  1  20   2  19  19   1   2  20   0
   20  40   0 200  41   4   0   0
      2   0   0 200  86   0   0
       20   0   0   2   0   0
         39   0   6  12   0
           43 176  29   0
             27 168   0
               11   0
                  1
BEST TRANSLATION: 10055 S</s>  :0-0 : pC=0.000, c=-0.519 [0..8] 9016
[total=-6.947]<<-5.646, 0.000, -17.078, -0.975, -11.623, -8.514,
-23.155, 4.000, 4.000>>
??? ?? ? ?? ? ? ?? ? ? ? ?

Trans Opt 0 [0..8]: [8..8]=</s>    [0..7]=S  : S ->S</s>  :0-0 : pC=0,
c=-0.519086 -6.94668<<-5.64583, 0, -17.0777, -0.974503, -11.6227,
-8.51364, -23.1549, 3.99959, 3.99959>>
Trans Opt 0 [0..7]: [7..7]=X   [0..6]=S  : S ->S X :0-0 1-1 :
pC=0.999896, c=0.999896 -7.38058<<-5.21153, 0, -17.077, -0.974503,
-11.6227, -8.51364, -23.1549, 3.99959, 3.99959>>
Trans Opt 0 [0..6]: [3..6]=X   [0..2]=S  : S ->S X :0-0 1-1 :
pC=0.999896, c=0.999896 -8.60037<<-4.77724, 0, -17.0175, -0.9619,
-11.5975, -7.04926, -22.7336, 2.99969, 2.99969>>
Trans Opt 0 [0..2]: [2..2]=X   [0..1]=S  : S ->S X :0-0 1-1 :
pC=0.999896, c=0.999896 -3.05231<<-1.73718, 0, -5.89485, -0.9619,
-4.65396, -6.35611, -9.23707, 1.99979, 1.99979>>
Trans Opt 0 [0..1]: [1..1]=X   [0..0]=S  : S ->S X :0-0 1-1 :
pC=0.999896, c=0.999896 -2.31227<<-0.868589, 0, -4.07733, 0, 0,
-5.66296, -6.04736, 0.999896, 0.999896>>
Trans Opt 0 [0..0]: [0..0]=<s>   : S -><s>  :: pC=0, c=0.434294
0.434294<<-0.434294, 0, 0, 0, 0, 0, 0, 0, 0>>
Trans Opt 0 [1..1]: [1..1]=he  : X ->??? :: pC=-2.14208, c=-3.88913
-3.88913<<-0.434294, 0, -4.36269, 0, 0, -5.66296, -6.04736, 0.999896,
0>>
Trans Opt 0 [2..2]: [2..2]=revolutionized  : X ->?? ? :: pC=-1.69976,
c=-2.8204 -2.8204<<-0.868589, 0, -3.97844, -0.9619, -4.65396,
-0.693147, -3.18971, 0.999896, 0>>
Trans Opt 0 [3..6]: [6..6]=painting   [5..5]=ink   [4..4]=japanese
[3..3]=the  : X ->?? ? ? ?? ? ? ? :: pC=-4.02668, c=-7.27479
-7.27479<<-3.04006, 0, -12.5763, 0, -6.94358, -0.693147, -13.4966,
0.999896, 0>>
Trans Opt 0 [7..7]: [7..7]=.  : X ->? :: pC=-0.184696, c=-0.720382
-0.720382<<-0.434294, 0, -1.93996, -0.0126031, -0.025123, -1.46439,
-0.421262, 0.999896, 0>>

I would expect the translation to use terminals other than "X" and
"S", but it seems to be not using syntactic labels at all (for any of
the sentences, not just the first). I've attached part of the rule table and
glue rule files, any clues about why it isn't using any syntactic
information in translation?

Thanks in advance,
Graham


_______________________________________________
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

Re: [Moses-support] tree-to-string training

Reply via email to