Hello all,
I am trying to use caching option of Irstlm ,
So I have config it with -enable-caching
the lm is made,
then I tried to compile and change it to ARPA format:
compile-lm lm --text yes out
but it gives this error:
Reading
Hello,
Thank you. Yes actually.
I was doubtful about details. The paper help a lot.
On Fri, Jan 27, 2012 at 8:40 PM, moses-support-requ...@mit.edu wrote:
Send Moses-support mailing list submissions to
moses-support@mit.edu
To subscribe or unsubscribe via the World Wide Web, visit
Hello,
Is it possible to tell me final and heuristics complete the alignment
table please?
-
Best Regards,
S.Bakhshaei
After All you will come
And will spread light on the dark desolate world!
O' Kind Father! We will be waiting for your affectionate hands ...
Hello,
We intend to add XML tags to our corpus but we are not sure how the Moses
decoder and SRILM uses these tags in training and decoding phase.
For example if we tag 19 in main corpus like this:
19 --- num19/num
How does LM must be made on this tagged corpus using SRILM?
Does SRILM consider
was the closer
to the average of all the BLEUs?
** we choose the best BLEU, hoping we have cached a better optimum point
and use its moses.ini.
Best Regards,
On Wed, Nov 23, 2011 at 8:14 AM, Jehan Pages je...@mygengo.com wrote:
Hi,
On Tue, Nov 22, 2011 at 10:18 PM, somayeh bakhshaei
s.bakhsh
Hello all,
Salam,
I am using moses in this way:
train,
for i=1 to 3
tune
end for
decode
evaluate
in the above loop for something unexpected happens, in large execution
sometime the weights produced in moses.ini are wrong. For example once it
produce 3 in the other case produce 4, take a
this can help you.
Best wishes!
Pidong
On 22 November 2011 16:57, somayeh bakhshaei s.bakhsh...@gmail.comwrote:
Hello all,
Salam,
I am using moses in this way:
train,
for i=1 to 3
tune
end for
decode
evaluate
in the above loop for something unexpected happens, in large execution
Hello,
How can I give different weights to multiple existing corpora
Does this code works?
plain2snt.out txt1 txt2 -weight w
--
Best Regards,
S.Bakhshaei___
Moses-support mailing list
Moses-support@mit.edu
Dear Dr. Koehn,
for grouping the input tokens (like the man), isn't there any solution by the
help of XML tags?
--
Best Regards,
S.Bakhshaei
--- On Fri, 6/10/11, moses-support-requ...@mit.edu
moses-support-requ...@mit.edu wrote:
From: moses-support-requ...@mit.edu
Hello All,
If I want to use XML tags what tags we can use more than n .. /n and np
.. /np according to:
http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc4
--
Best Regards,
S.Bakhshaei___
Moses-support mailing list
Hello,
1) check if there is any | token in your train file or not. There must not
exist any then it will cause to error.
2) have you correctly set MACHINE_TYPE variable?
--
Best Regards,
S.Bakhshaei
--- On Wed, 1/5/11, moses-support-requ...@mit.edu
Hello,
I have problem with the multi-reference tuning.
Actually i don't know how the input format should be?
I have test this one:
mert.pl src ref0 ref1 ref2 ...
but it gives error !
--
Best Regards,
S.Bakhshaei
___
Hello,
two question:
1) I want to produce monotone translation, I have removed the -reordering msd..
from calling train-factored-phrase.model, but stilll there is a distance base
reordering, how I ca disable it ? Is it a good job to change the distortion
model weight:[weight-l] to 0 in
Hello,
In the theory we learn that the null token is place in the beginning of
each sentence. But in the output file of a real system it is seem there
is not such a token implicitly.
--
Best Regards,
S.Bakhshaei
___
Hello,
Are the order of the phrases in the phrase table same as the sentences corpus?
i mean for example
phrases 0-n extracted from sentences 1
phrases 0-k extracted from sentences 2
phrases 0-j extracted from sentences 3
and so on
--
Best Regards,
S.Bakhshaei
Hello,
I have my own extract and extract.inv,
Is there any way that i make extract.o from these two?
--
Best Regards,
S.Bakhshaei
___
Moses-support mailing list
Moses-support@mit.edu
Hello,
I have some question about mteval-v11b.pl
1) It can not use multi-reference with mteval what is a equivalent tool for
this aim?
2) I tried multi-bleu.perl, but the scores reduced ! while we expect to
increase while adding more reference sets !! How it is may?
3) I test mteval-v11b.pl
: Contents of Moses-support digest...
Today's Topics:
1. mteval-v11b (Somayeh Bakhshaei)
2. Re: mteval-v11b (liu chang)
3. Re: mteval-v11b (Miles Osborne)
4. Re: mteval-v11b (Ondrej Bojar)
--
Message: 1
Date: Sun, 17 Oct
Dear All,
Unfortunately i recently give a new error that don't know what is the reason.
There seem an incompatibility in my system because:
I have set the lm order to 5 in all the steps but in tuning step this errors
happes?!
moses: LanguageModelInternal.cpp:23: virtual bool
Hello,
How I can change the Giza++ configuration in training
step of moses? for example changing the iteration of IBM models, This
is the default setting that moses uses:-m1 5 -m2 0 -m3 3 -m4 3 I want
to change it but i don't know how!
--
Best Regards,
S.Bakhshaei
Hello,
How it is may that moses translate one sentences into two sentences ?!!
This is what is happening in my test set.
--
Best Regards,
S.Bakhshaei
___
Moses-support mailing list
Moses-support@mit.edu
: Hieu Hoang hieuho...@gmail.com
Date: Sat, Sep 11, 2010 at 4:10 AM
Subject: Re: [Moses-support] weighting alignment links
To: moses-support@mit.edu
On 11/09/2010 11:30, Somayeh Bakhshaei wrote:
Hello,
We need to weight some links of the alignment file. Is there any routine way?
What
Bakhshaei s.bakhsh...@yahoo.com wrote:
From: Somayeh Bakhshaei s.bakhsh...@yahoo.com
Subject: weighting alignment links
To: moses-support@mit.edu
Date: Saturday, September 11, 2010, 5:31 PM
actually we want to effect the system by repeating the important links, Is it
wrong to change:
0-0 1-1 2-2
Hello,
I checked the mailing list archive for the answer of how to add dictionary to
Moses , The answer i found is that the best way is by adding it to corpus like
extra one word sentences.
Is it correct?
Then at the end of each word a point must be added?
--
Best Regards,
Dear All,
I have change reordering to :
-reordering monotonicity-bidirectional-fe
-reordering monotonicity-bidirectional-f
-reordering monotonicity-fe
-reordering monotonicity-f
but i receive this error! What is wrong?
Saved: ./run1.moses.ini
Normalizing lambdas: 0 1 1 1 0.3 0.2 0.3 0.2 0
Dear All,
Hi,
I need to change the corpus after running Giza++. I mean i want to use
different kind of corpus for these steps: making alignment models and
extracting phrases.
I should change train-factored-phrase-model.perl. is it enough to rm the old
corpus and cp new one like this
Hello All,
I want to know is there any TER evaluation tool which can be used for scoring
moses output ?
Best Regards,
S.Bakhshaei
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
Hi,
In one of the previous emails i have seen that the maximum phrase length is 7
by default, but know i found in the moses-cmd/src/moses comments that it is 20.
I have done a lot of wrong tests if so!!
can anyone say which one is correct Please : 7 or 20 ?
--
Best Regards,
Hi,
I don't find how much is the beam search limit ( -b ) by default!
Where the parameters like -b, -s, are set ?
What is a good value for s b ?
Can you help me please?
--
Best Regards,
S.Bakhshaei
___
Moses-support mailing
Hi,
Is it possible that moses produces an over fitted model?
How it can be checked?
How it can be avoided?
--
Best Regards,
S.Bakhshaei
--- On Sun, 3/21/10, moses-support-requ...@mit.edu
moses-support-requ...@mit.edu wrote:
From: moses-support-requ...@mit.edu
Hello everybody
How it is may that i increase the LM order, but the Bleu score of the output
decreases?!
If i use a higher LM order should i mention it explicitly in the train part,
phrase extraction , evaluation , ... ?
--
Best Regards,
S.Bakhshsaei
files.
Also I have written a java code to do it for me. If you had problem with
solving this error , say me to send you the code.
Best Regards,
Somayeh Bakhshaei
--- On Mon, 3/8/10, moses-support-requ...@mit.edu
moses-support-requ...@mit.edu wrote:
From: moses-support-requ...@mit.edu moses
Hi every body,
I am at the end of running moses, :)
my last problem is that i have problem with evaluation of the translation .
i there any tools that makes sgm format for the source target files?
actually i write a code do it, but still i receive nothing as the bleu out put.
this is the out
Hello,
I am in the step of Train Phrase Model, but i am stopped with this error, It
seems this is caused by Giza++, but i can run Giza++ on my corpus out of moses
instruction , completely successfully, but in moses i see:
parameters modifying the EM-algorithm:
Hello
I am running moses in utf8 format too and in the phrase extraction step gives
the same problem as Guillem Mass? Sanabre (message 7) says, the same error
but at the end stop with signal 11:
died with signal 11, without coredump
I changed the utf8 format by using buckwalter , but still
Hi everybody
I am a new user of Moses!
I want to start it but i wants to know if Moses works only on Linux?
Is it possible be run it on windows?
Thanks alot
___
Moses-support mailing list
Moses-support@mit.edu
36 matches
Mail list logo