ial
Within the next days, we will provide a new tutorial with highlights
some of the new features.
feed-back, bug reports and contributions are welcome !
--
Holger Schwenk
membre IUF sénior
professeur en Informatique
LIUM - Université du Maine
email : schw...@lium
ernatively any other code that does the same and
> can also deal with sparse features, please let me know. I'd prefer to
> not spend any time at all on implementing this myself, as I'll probably
> need to run it only a few times for testing purposes.
>
> Cheers,
> Matt
Hello,
another option is to perform data selection to only keep the data
relevant to yout task.
Usually you improve your performance, and as a nice side effect, you LM
is much smaller ;-)
Many people use the algorithm proposed by Moore and Lewis, which is
implemented in the freely available
short drive away ...
Applications should include an CV, a list of publications and the name
of two references. We will invite interesting candidates for further
discussions.
For more information, please contact Holger Schwenk by email:
holger.schw...@lium.univ-lemans.fr
Moses-support@mit.edu <mailto:Moses-support@mit.edu>
http://mailman.mit.edu/mailman/listinfo/moses-support
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
--
Holge
On 04/29/2013 06:56 PM, Wei-Yun Ma wrote:
> Hi,
>
> I have a question about how to do reranking of the N-best list that Moses
> generated.
>
> For example, for one sentence, I got 100 N-best translations from Moses,
> and now I want to use some other complicated sentence-based features to
>
Hello,
I haven't used suffix arrays lately, but in the past they were only used
for the forward translation probabilities, and not for the backards ones
(due to complexity issues). This can result in a loss of 1 point BLEU.
Holger
On 02/15/2013 11:32 AM, Mirkin, Shachar wrote:
Hi,
I've b
On 02/13/2013 12:04 PM, Peled Guy wrote:
Hi,
We are developing a Transliteration machine and we have a problem
taking evaluation of Top2\Top5\Top10 results from Moses.
When we tell Moses to give us *n-best-list* we get duplication of
words, for example:
3 |||c a r d i n a l s ||| d: 0 -0.55
Hello,
I just installed Fedora Core 17(kernel 3.6.10, gcc 4.7.2, boost
1.48.0-13) and I get an error while compiling the latest version of Moses:
./bjam -j4 --with-srilm=$SRILM --with-giza=/usr/local/bin
--prefix=/opt/mt/moses-smt/moses-2012-12-28
fails with
moses/FeatureVector.cpp:284:17
On 06/05/2012 06:45 PM, Philipp Koehn wrote:
> Hi,
>
>> An intermediate step could be to use the CSLM to rescore lattices which
>> are likely to be a much richer dump of the search space than n-best
>> lists. Can Moses create lattices which include all the (14) feature
>> function scores ?
> When u
On 06/04/2012 01:50 PM, Lane Schwartz wrote:
> Marcello,
>
> A GPL project can definitely use components from an LGPL project. So
> in the worst case, integration of the two could be done, distributing
> the whole combined work as a modification of CSLM. Not that I'm
> proposing we do that.
>
> In
following
publications:
[1] Yoshua Bengio and Rejean Ducharme. A neural probabilistic language
model.
In NIPS, vol 13, pages 932--938, 2001.
[2] Holger Schwenk, Continuous Space Language Models; in Computer Speech and
Language, volume 21, pages 492-518, 2007.
[3] Holger Schwenk,
-lium.univ-lemans.fr/~schwenk.
Applications and inquiries should be sent to Holger Schwenk
(holger.schw...@lium.univ-lemans.fr). Salaries start at 2500 Euros net
per month, including health care and other social benefits. The
position is immediately available and is open until filled
projects can be found at
http://www-lium.univ-lemans.fr/~schwenk.
Applications and inquiries should be sent to Holger Schwenk
(holger.schw...@lium.univ-lemans.fr). Salaries start at 2500 Euros net
per month, including health care and other social benefits. The
positions are immediately available
On 12/29/2011 10:57 AM, Bill_Lang(Gmail) wrote:
> Hi Moses Friends,
> These days, I am running phrase based and hierarchical based
> moses. Here my training corpus is FBIS (240k sentence pairs) for
> Chinese to English translation. My moses version is updated on Dec 19,
> 2011. After trainin
Hello,
I spotted a minor bug in line 387 of moses-chart-cmd/src/IOWrapper.cpp,
revison 4200
one need to change
out << "w: ";
to
out << " w: ";
e.g. a space before "w:". Logically, we should do the same for "lm:",
but this has no consequences.
This corrects the wrong output of n
The computer science laboratory of the University of Le Mans (LIUM)
(http://www-lium.univ-lemans.fr/en/content/language-and-speech-technology-lst)
was recently awarded two major international grants and we are seeking
to substantially expand the group working on statistical machine
translation.
in about 1 hour by high speed train.
For information, please contact Holger Schwenk by email:
holger.schw...@lium.univ-lemans.fr
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
18 matches
Mail list logo
