Hi All,
I am trying to train system for Urdu and for that I want the corpus to be well
tokenized. So I wanted to know that is it possible to tokenize the Urdu corpus
using the available list of words?--
Kind Regards,
Mr. Asad Abdul Malik
___
Hi All,
I've trained system which is able to translate from language A to language B
and it is working pretty fine. Now I've trained system for translating from
language B to language A. but it is not working. I've changed the language
model directory and working directory for it. But it is
Hi All,
I've trained the english to urdu phrase based SMT. Now I wanted to add the
dictionary to the system for those words which are converted in target text. So
is it to add dictionary to the trained system? --
Kind Regards,
Mr. Asad Abdul Malik
Hi All,
I am currently trying to develop the parallel corpus. I wanted to know is there
any tool with which I can develop it? i.e. The sentence in source language is
at same line in target language. --
Kind Regards,
Mr. Asad Abdul Malik
___
Hi All,
I am trying to use EMS and for that I have to fulfill the requirements. I've
installed SRILM, Graphviz ImageMagick, but now I am unable to install the
GhostView tool. I've gone through their documentation and have configure and
build this package but unable to install this. When I
Hi All,
I am trying to use EMS and for that I have to fulfill the requirements. I've
installed SRILM, Graphviz ImageMagick, but now I am unable to install the
GhostView tool. I've gone through their documentation but I am not
understanding that how can I install it. I'm searching for it from
Hi All,
I am installing Moses and following the manual for it. But I am confuse that
where I have to save the Boost, MGIZA and other required tools?
--
Kind Regards,
Mr. Asad Abdul Malik
___
Moses-support mailing list
Moses-support@mit.edu
Hi All,
I am installing moses for which I have to install MGIZA. While installing I
came to this line but I am confused that how to use it. as I am getting error
of not a valid identifier
export BINDIR=~/workspace/bin/training-tools --
Kind Regards,
Mr. Asad Abdul Malik
Hi All,
How can I Run experiment.perl -config config.toy -exec.
When I type following command:
$ run experiment.perl -config config.toy -exec
It says no command found. --
Kind Regards,
Mr. Asad Abdul Malik
___
Moses-support mailing list
Hi All,
I am trying to run EMS and for that I have to install GhostView, I've
downloaded it and gone through it's manual but I didn't find any procedure for
installation. I've also emailed the support group of GNU but they aren't
responding. I was thinking that may be any of you have installed
Hi All,
I am tokenizing my corpus and have entered the command but it is taking to
long, I just wanted to know that how much time it will take?
P.S. the corpus is same, may be around 1000 sentences, and in french language.
Kind Regards,
Mr. Asad Abdul Malik
Hi All,
I currently wanted to develop String to Tree SMT, I've successfully developed
Phrase Based SMT using MOSES for Urdu (source) and English (target). Now I
wanted to developed the String to Tree SMT for these two languages. I am still
confused that how will I develop such a system.
Have
Hi All,
I am currently trying to develop SMT system, and for that I have parallel
corpus, but the problem is that I have parallel corpus in XML format and upto
my knowledge MOSES support TXT. So is there any way that I can convert XML to
TXT so that I don't change the format also.
PS. I've
Hi All,
I've successfully developed Phrase Based Statistical Machine Translation for
Urdu to English. Now I wanted to move forward to the Syntax Based. I wanted
to know that how can I develop Syntax Based SMT? Do I need linguistic rules in
order to develop it?
Thanks,
Mr.
Hi All,
I've generated languge model for my corpus and in the output file there is
value before and after each word i.e.
-2.625965 Title -2.148461
So what does these number means?
Kind Regards,
Mr. Asad___
Moses-support mailing list
for some languages.
Have a look here for some experiments with GT and en-cs. You could try
similar experiments with a language pair that you know.
http://ufal.mff.cuni.cz/mtm13/files/13-constituency-vs-dependency-ondrej-bojar.pdf
cheers - Barry
On 16/04/14 06:33, Asad A.Malik wrote:
Hi All,
I
Hi All,
I wanted to know that which statistical technique is Google translate using
currently?
Also what steps did Google translate takes in order develop translation system.
I didn't find any proper reference about Google translate. I would really
appreciate your help.
Regards
Asad
Hi All,
I've developed Urdu to English SMT using MOSES, and it is currently giving me
BLEU score of 8. Now I wanted to improve its translation so that it gives me
higher BLEU score.
Regards
Asad A.Malik___
Moses-support mailing list
Hi All,
I've developed Urdu to English SMT using MOSES, and it is currently giving me
BLEU score of 8. Now I wanted to improve its translation so that it gives me
higher BLEU score.
Regards
Asad A.Malik___
Moses-support mailing list
Hi All,
I am trying to reinstall MOSES and for that I have to install Boost. So I
wanted to know that if the command
sudo apt-get libboost-all-dev
is enough or I have to manually install it?
Regards
Asad A.Malik___
Moses-support mailing list
Hi All,
I am trying to install MOSES, I've followed steps of user manual. but when I
try to run decoder on sample-models then there is no moses in the :
~/mosesdecoder/bin/
and also there is only config.log file in ~/mosesdecoder/bin . I dont know what
is the problem. I've cloned the moses
Hi All,
Due to less space in my Ubuntu drive, I tried to extend it. But before doing
that I backuped my whole MOSES directory. And during extending I was in a
situation where I have to reinstall Ubuntu 12.04. And after installing it I
copied the MOSES directory back to Ubuntu drive, but now
Hi All,
I am installing Moses and I've installaed boost 1.55 as
mentionedhttp://www.boost.org/doc/libs/1_55_0/more/getting_started/unix-variants.html;.
And then I downloaded MOSESDECODERfrom:
github.com/moses-smt/mosesdecoder.git
to the moses directory after that when I enter following
here is the screen shot
Regards
Asad A.Malik
On Saturday, January 4, 2014 12:11 PM, Asad A.Malik asad_12...@yahoo.com
wrote:
Hi All,
I am installing Moses and I've installaed boost 1.55 as mentioned
http://www.boost.org/doc/libs/1_55_0/more/getting_started/unix-variants.html
Hi All,
I am trying to develop Urdu SMT using MOSES. I have Urdu parallel corpus and
the 1st step in manual is to tokenize the corpus, but when I enter following
command:
~/SMT/mosesdecoder/scripts/tokenizer/tokenizer.perl -l ur
~/SMT/corpus/training/mycorpus.ur-en.ur
Hi All,
I've in the Testing phases, and I've binarised phrase and lexical table by
given commands in Moses manual. And also copied moses.ini in binarised
directory.
But I don't know how to do following.
1. Change PhraseDictionaryMemory to PhraseDictionaryBinary
2. Set the path of the
Hi All,
In the manual there i mentioned that using command --decoder-flags=-threads 4
we can use MOSES multi-threaded. But I am getting following message.
PS. I have C2D system. I think I'll use 2 instead of 4 in the given command
Regards
Asad A.Malik
Multithread error
Description: Binary
Hi All,
I am using MOSES for the 1st time and following the steps shown in the manual,
but I am unable to prepare corpus (i.e. tokenization). I've also attached image
of the terminal.
Previously I've tried this step and it generated the
outputnews-commentary-v8.fr-en.tok.en. but now it is
I am using windows 8 and wanted to use Moses on it. I've installed Cygwin and
the packages which are required for it. After that I am unable to install boost.
I've also tried the package in which you don't have to build Moses from source
but that isn't working
. But actual I want (any one of three mentioned techniques)
that is easy to develop and don't require much of human effort.
Kindly help me in
selecting the technique and show me the right path. I will really appreciate
your help.
Regards
Asad A.Malik
30 matches
Mail list logo