hi marcin
no. There's a similar boolean,
m_needAlignmentInfo
but it's not quite the same. It won't be turned on if outputting word
alignment is not requested.
I've changed your compact pt code to use this but you may wanna check it.
If you can give me a small set of commands and excamples
Hi,
I am afraid that the distance-based reordering model is hard-coded
but you could just set its weight to 0.
-phi
On Wed, Nov 14, 2012 at 3:18 PM, saeed farzi wrote:
>
> Dear members,
>
> I wanna add my reordering model in moses and i need disable distortion model
> . would you plz tell me ho
Dear members,
I wanna add my reordering model in moses and i need disable distortion
model . would you plz tell me how to do this.
tnx in advance,
--
S.Farzi, Ph.D. Student
Natural Language Processing Lab,
School of Electrical and Computer Eng.,
Tehran University
Hi Hieu,
Is the boolean parameter corresponding to -use-alignment-info in
StaticData still present?
W dniu 14.11.2012 20:56, Hieu Hoang pisze:
The decoder flags for word alignments have been cleaned up a little.
They were overlapping or didn't work.
These are the ones that work:
-print-al
The decoder flags for word alignments have been cleaned up a little. They
were overlapping or didn't work.
These are the ones that work:
-print-alignment-info-in-n-best [true/false]
-alignment-output-file [filename]
The following were deleted:
-use-alignment-info
Can be inferred if e
Hi,
> mrodoje@ubuntu:~/corpus$ ~/mosesdecoder/scripts/tokenizer/tokenizer.perl
> -l en < ~/corpus/training/europal-v7.de-en.en \
> >~/corpus/europal-v7.de-en.tok.en
>
> but got the following error
>
> bash: /home/mrodoje/corpus/training/europal-v7.de-en.en: No such file or
> directory
>
> How do I
Hi Nicola,
I am very familiar with the way smoothing works with Kneser Ney, but
I have no idea how to properly handle singleton pruning.
But be this as it may:
In the example I cite, the trigram "schválení těchto zpráv" occurs only
in one context: following "proti". Why is it included in the ngr
Nicola,
On an unrelated note, could you say why the smoothing technique is
called Modified ShiftBeta in IRSTLM. I know it was originally called
Improved Kneser-Ney and sometimes "Simplified" Kneser-Ney (Interspeech
2008), which hinted that it varied from the original description of
Modified Kneser
Yep it's a pain and I've had to write a fair amount of code to work
around this. By default, SRI prunes n-grams of order 3 or above if the
adjusted count is 1. For the highest order, the adjusted count is the
raw count. For all other orders, the adjusted count is the number of
unique words t
Modified ShiftBeta (aka modified Kenser Ney) does not considered the real
counts for computing probabilties, but the corrected counts, which basically
are the number of different successors of a n-gram.
Hence in this case your bigram "schválení těchto" occurs always before "zpráv",
and hence it
Department 4.6
Applied Linguistics, Translation and Interpreting, Saarland
University, Germany
is inviting applications for*two* three-year Early Stage Researcher
pre-doctoral positions in corpus-based approaches to machine
translation. The positions are part of the new EU Fra
Hi,
I encountered the same problem when using "msb" and
pruned singletons on large corpora (Europarl).
SRILM's ngram complaints about "no bow for prefix of ngram"
Here a Czech example:
grep 'schválení těchto' /home/pkoehn/experiment/wmt12-en-cs/lm/europarl.lm.38
-2.35639schválení těchto
Hi Barry,
I downloaded the French-English europal parliament corpus for the translation
system from the provided link wget
http://www.statmt.org/wmt12/training-parallel.tgz.
However, the training folder contain German - English corpus.
The files in the training folders are europarl-v7.cs-en.cs,
Dear Colleague,
QT LaunchPad ( www.qt21.eu/launchpad ) is a two-year project funded by the
European Commission which focuses on quality translation. As part of the
initial work for this project, the consortium is surveying the needs and
expectations of relevant stakeholder groups.
We would ve
Hi Henry
The simplest way to get the release is to go to the following page
(linked as "latest release" on the Moses website):
https://github.com/moses-smt/mosesdecoder/tree/RELEASE-0.91
Then click on the "ZIP" button towards the top left of the page. This
should unzip to a directory called "mo
Hi folks,
We are planning to build a system on Moses 0.91 version. When I got to
the github page of 0.91 by clicking the link on Moses site, I was
confused how to download this version. First I cloned it from
git://github.com/moses-smt/mosesdecoder.git
Got 112M files on mosesdecoer directory.
S
Hi Federico,
Please check the compilation instructions in BUILD-INSTRUCTIONS.txt --
it has a list of comprehensive steps to compile Moses, and also gives
instructions on how to install dependencies (e.g. Boost).
Best,
Nick
On 11/13/2012 12:18 PM, f.fancellu wrote:
Hi,
I am trying to run the
17 matches
Mail list logo
