Thank you John for your reply, but I see that the link doesn't work.
Bests
2016-05-22 18:41 GMT+02:00 Burger, John D. <j...@mitre.org>:
> Not sure if this is what you want:
>
> http://iwslt2010.fbk.eu/node/58
>
> - John Burger
> MITRE
>
> > On May 22, 2016,
Hello,
I am looking for a BTEC corpus, but cannot find it on IWSLT website.
Can you help me to find it
Thank you
Bests
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
Hello,
I would like to know if there is a paper which describe how Moses do to
select the best translation when We use 2 differents translation tables.
Best regards
___
Moses-support mailing list
Moses-support@mit.edu
that they are of different difficulty.
Phrase-based models have some deficiencies when it comes to German, such as
translation of compounds, and long distance reordering. We are having
more success with syntax-based models for this language pair.
-phi
On Thu, Nov 13, 2014 at 5:58 PM, Cyrine NASRI
cyrine.na
Hello,
I'am trying to build the baseline SMT for english to german language. I've
got a strange problem because i work for the 1st time on german language
and i've got a score Bleu on Dev corpus = 16 and on the test corpus = 9 !
i prepared the corpus before training and mert as usual like this:
Thank you Tom for your reply.
So i keep these quot; co in the language model too?
Bests
2014-06-18 16:04 GMT+02:00 Cyrine NASRI cyrine.na...@univ-lorraine.fr:
Hello
I have concern the tonkenizer script,
When i so the tokenization, i got some quot; and apos;.. wHen i let
them
Hello
I have concern the tonkenizer script,
When i so the tokenization, i got some quot; and apos;.. wHen i let
them in the training process i think it damage the translation quality?
So should i really let them or transform them to and ' after training.
Thank you in advance for your reply
Hello,
I have a question concern Mert-moses: Is it possible in Moses to do Mert on
XML files?
Is there any option to do this, or should i delete the XML tags manually
before doing MERT?
Thank you in advance
Bests
Cyrine
___
Moses-support mailing list
= 0.5
Before we change 0 by 1 in the config file:
Any idea please?
Thnks
Best regards
--
*Cyrine NASRI
Ph.D. Student in Computer Science*
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
for your replies
Best
--
*Cyrine NASRI
Ph.D. Student in Computer Science*
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
filtered/moses.ini at
./mert-moses.plline 1271.
*
Any idea please?
Thank You
--
*Cyrine NASRI
Ph.D. Student in Computer Science*
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
Dear all,
I have a question concern evaluation step.
I see in the tutorial that we have to Recase and Detokenize the output.
But i don't know exactly the reason for doing this
Any explanation please?
Thank you
Best regards
--
*Cyrine
Ph.D. Student in Computer Science*
Hello to all,
I'd like to know how to integrate other features in the translation table other
than the five features generated by default.
How we can modify the configuration file moses.ini for that.
thank you
Bests
--
*Cyrine
Ph.D. Student in Computer Science*
for
maintenant
2013/1/13 Cyrine NASRI cyrine.na...@gmail.com
Hi Prashant,
thank you for your answer,
How the phrase is translates verbatim? any explanation please?
Thnks
Bests
cyrine
2013/1/13 Prashant Mathur prash...@fbk.eu
Prashant
--
*Cyrine NASRI
Ph.D. Student
Hello all,
I have a question concern decoding :
I run mert to translate this frensh sentences: j espère qu 'il change
manitenant'
Moses translates it as : i hope that it changes now
In the phrase table there are these phrases :
j espère ||| i hope ||| .
qu 'il ||| that it |||
But
Hi Prashant,
thank you for your answer,
How the phrase is translates verbatim? any explanation please?
Thnks
Bests
cyrine
2013/1/13 Prashant Mathur prash...@fbk.eu
Prashant
--
*Cyrine NASRI
Ph.D. Student in Computer Science*
___
Moses
Hello all,
I'd like to know how to use the script wrap-xml.perl to change a texte file
to a xml format. If possible the general syntax.
Bests
--
*Cyrine
Ph.D. Student in Computer Science*
___
Moses-support mailing list
Moses-support@mit.edu
Cheers and best,
Christian
On Nov 6, 2012, at 3:57 PM, Cyrine NASRI wrote:
Hello all,
I'd like to know how to use the script wrap-xml.perl to change a texte
file to a xml format. If possible the general syntax.
Bests
--
Cyrine
Ph.D. Student in Computer Science
Hello all,
I have a problem with mert script
i launch this command to do the tuning :
./mert-moses.pl
/home/paro/MOSES/corpus/Texte.tok.low.fr/home/paro/MOSES/corpus/Texte.tok.low.en
/home/paro/MOSES/moses-smt-mosesdecoder-1cbf457/bin/moses
/home/paro/MOSES/corpus/moses.ini
Hello all . I have à general question about Count lexical weights. If we
use a method which does not use alignements between words , is it
mandatory to use lexical weights in the phrase table ? Tanks . Bests
___
Moses-support mailing list
at 2:14 PM, Cyrine NASRI cyrine.na...@gmail.com
wrote:
Hello all . I have à general question about Count lexical weights. If we
use
a method which does not use alignements between words , is it
mandatory to
use lexical weights in the phrase table ? Tanks . Bests
/moses/?n=FactoredTraining.ScorePhrases
** **
Best,
Daniel
** **
*Von:* moses-support-boun...@mit.edu [mailto:moses-support-boun...@mit.edu]
*Im Auftrag von *Cyrine NASRI
*Gesendet:* Sonntag, 22. April 2012 22:59
*An:* moses-support@mit.edu
*Betreff:* [Moses-support] features
Hello all,
i have a question concern reordering model
in the model i have this string :
@ ries bibliothèques ||| @ ries ||| 0.60 0.20 0.20 0.20
0.20 0.60
Can you explain me what these numbers refers to? how Moses calculate them?
Thank you
Bests
--
*Cyrine NASRI
Ph.D
Hi all
I have a stange problem with Mert wich it happens for the first time:
When i do the mert. the programme stopp in the middle of the first iteration
and i got this error message :
moses: PDTAimp.h:284: void
Moses::PDTAimp::CreateTargetPhrase(Moses::TargetPhrase, const
std::vectorconst
STDERR and STDOUT
and send all to me together with your input file (if not too big)
best regards,
Nicola Bertoldi
On Sep 4, 2011, at 6:51 PM, Cyrine NASRI wrote:
Hello, I'm a new user with irstlm
I want to build a 3gram with irstlm but i have an error message :
./build-lm.sh -i
Hi all,
Is it possible tu uses 5 gram Language model built bu SRILM with MOses?
Thanks
Best
Cyrine
--
*Cyrine
Ph.D. Student in Computer Science*
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
Hello, I'm a new user with irstlm
I want to build a 3gram with irstlm but i have an error message :
./build-lm.sh -i Texte_EN.txt -n 3 -o lm -k 3
Cleaning temporary directory stat
./build-lm.sh: 145: Syntax error: Bad fd number
Can you help me please?
Thanks
Best Regards
Cyrine
Good evening,
I have a weird message that appears when I run the MERT:
Use of uninitialized value within @WORD_FACTOR in concatenation (.) or
string at
/home/cyrine/Desktop/moses13Janvier/moses-scripts/scripts-20110114-0915/training/
filter-model-given-input.pl line 191, INPUT line 294.
Use of
Hello,
Do you think the use of a reordering model is mandatory?
If we eliminate the reordering model from the configuration file but i leave
only the parameter -d, the reordering is maintained?
I ask this because before with the Pharaoh decoder, I do not include the
reordering model
Thank you
Dear all,
I have a strange question...
I have a phrase table which is not based on alignment, and I'd like to try
it into moses...
The standard Moses phrase table line contains also the lexical weights in
both the direction. I cannot compute the lexical weights because I have not
the alignment...
Hello everyone,
I try to follow the tutorial of Moses (step by step)
I got to level the creation of the translation table as shown in following
this order:
nohup nice tools/moses-scripts/scripts-*MMDD-HHMM*/training/train-model.perl
-scripts-root-dir
Hello everyone,
I have a problem with the extraction of phrases in Moses
I tested on two parallel corpora containing only not two long sentences,
it built a table of phrases not containing all the phrases:
Also I do not understand why it gives me :
!Use of uninitialized value $a in scalar chomp
hello sir Koeh,
I am very happy to answer me, thank you.
Let me explain from the beginning:
I created a translation table using triggers (Smail and all)
I have not used Giza or moses to create it.
I work on a development corpus of 1440 sentences.
My goal now is to calculate the score blue for
Hello everyone,
I have a question about the MERT
I tried started with small example (sample model).
with a translation table like this:
der ||| the ||| 0.3 ||| |||
das ||| the ||| 0.4 ||| |||
das ||| it ||| 0.1 ||| |||
das ||| this ||| 0.1 ||| |||
die ||| the ||| 0.3 ||| |||
ist ||| is ||| 1.0 |||
:
[ttable-file]
# 0 0 0 1 /media/Vista/moses/moses/misc/table-trad-totale
1 0 0 1 /home/cyrine/tools/moses/misc/tabledeTRAD1EN-FRAncien.txt
Any idea please
Thank you
Bests
--
Cyrine NASRI
___
Moses-support mailing list
Moses-support@mit.edu
http
Hi everyone,
I have a problem of compilation Scripts Support of Moses. After downloading
the scripts.
I changed the makefile this way:
TARGETDIR? = / Home / cyrine / tools / moses-scripts
BINDIR? = / Home / cyrine / tools / bin
I can not compile scripts.
Can you help me?
Thank you
Cordially
Hello everyone,
I am using Ubuntu 64-bit and I try to install Moses. (I installed it before
without problems under 32bit)
When I executed this command:./regenerate-makefiles.sh
it myself out an error:
Calling ...
./regenerate-makefiles.sh: line 45:-I: command not found
aclocal failed
Can someone
Thank you Barry
So if I understand correctly, I am obliged to go through the nine steps
mentioned in the manual of Moses (page 103).
I'm still a beginner in the field of automatic translation.
Thank you
Have a nice day.
Cyrine
___
Moses-support mailing
I built my model and my language translation table.
So is there a need to go through Giza + +?
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
Hi Barry,
Thank you .
Thank you for your answer. Thus as that I return to the initial problem
concerningTuning. I' have my file intial moses.ini and my translation table
(of size 10GO).
I don't know why i should use the file moses.ini created by
train-factored-phrase-model.perl
All the time, the same problem.
I d'ont know why
Anyone can help me
Thanks a lot
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
Hello everyone,
I'm trying to do the tuning, but by typing this command, I get a message
that the option is missing an argument.
User @ user-laptop: ~ / Desktop / moses / moses / scripts / training $. /
Mert-moses-new.pl / home / Desktop / work / input / home / Desktop / work /
reference / home /
Thank you Zahurul,
it's ok, but there is no config.ini.
Predict 0
After default: -l mem_free=0.5G -hard
usage: mert-moses-new.pl input-text references decoder-executable
decoder.ini
Options:
--working-dir=mert-dir ... where all the files are created
--nbest=100 ... how big nbestlist to
Hi Barry,
When I make 1 0 0 5 , it says :
moses: StaticData.cpp:808: bool Moses::StaticData::LoadPhraseTables():
Assertion
`weightAll.size() = weightAllOffset + numScoreComponent' failed.
Abandon
So i think like Lee Ball said 0 0 1
Thank you
Best regards
Cyrine
Thank you Prof Koehn for your answer.
It's OK,
Thanks
2010/6/25 Cyrine NASRI cyrine.na...@gmail.com
Good morning everybody
I dont understand the meaning of* -nscores 5
**When i make the command wich *Binaryze the Phrase Tables, a message
appears to me processing ptree for 5
Can't read 5
Same problem
it cannot find the file
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
46 matches
Mail list logo