Yes, that will do it.
On Mon, Aug 9, 2010 at 4:13 PM, Sylvain Raybaud
wrote:
> On Monday 09 August 2010 20:43:53 Chris Dyer wrote:
>> I'm sorry I haven't had an opportunity to look into this yet
>> (hopefully later this evening). But, one thing that you need to do is
>> make sure that your config
On Monday 09 August 2010 20:43:53 Chris Dyer wrote:
> I'm sorry I haven't had an opportunity to look into this yet
> (hopefully later this evening). But, one thing that you need to do is
> make sure that your config file has an entry setting the maximum
> phrase size to a very large number, which p
I'm sorry I haven't had an opportunity to look into this yet
(hopefully later this evening). But, one thing that you need to do is
make sure that your config file has an entry setting the maximum
phrase size to a very large number, which prevents some bad pruning
from taking place that can lead to
SECOND CALL FOR PAPERS
--
"Bringing MT to the User: Research on Integrating MT in the Translation
Industry"
Second Joint EM+/CNGL Workshop (JEC 2010)
http://web.me.com/emcnglworkshop/JEC2010
-
Hi,
scores will differ for different test sets. If you randomly sample the test set
from you parallel data, they should be relatively similar, though.
You can compute confidence intervals with bootstrap resampling, which
will give you some indication how reliable a, say, 0.5, 1.0, or 2.0 point
di
Hi all,
Is there any body can help on this?
There might be some mistakes during the training of the Moses engine 2
(used the source language model), but the criterion to select the
sample data for BLEU/NIST score evaluation is still sth I want to
know/make sure.
Thanks so,
Wenlong
2010/8/7, We
Hello
Here is the latest version of the script, which replace noise information
with epsilon transitions. Moses successfully translates very small "toy"
lattice generated with this script but on a real world example
(http://perso.crans.org/raybaud/realworld.slf.gz) Moses fails with glibc
com
Philipp Koehn wrote:
> this is not correct - LM cost is in the future cost estimate.
> Obviously, this is a rather low probability, depending
> on if the language model was trained with open or
> closed vocabulary.
And also whether the word is unknown to the LM or not, yes? Typically
there are
Hi everyone,I would like to ask for some details on how Moses deals with the
handling of unknown words. As I read from the tutorial, unknown words are
copied verbatim to the output. However, it is not clear of how we deal with the
distortion limit while copying unknown words to the output.The si
Hi,
this is not correct - LM cost is in the future cost estimate.
Obviously, this is a rather low probability, depending
on if the language model was trained with open or
closed vocabulary.
The reordering of unknown words does cause often some
strange reordering, due to the fact that an unknown w
It seems like even if this is correctly implemented, unknown words
would be delayed until the edge of the window they are in, due to
trying to avoid paying the high LM cost until the last minute. LM cost
is not in the future cost, so hypotheses paying this LM cost should
lose to hypotheses delaying
Dear Mosers and Mosettes
For your delectation and degustation, we are rolling out a new version
of moses which adds a bunch of new features and fixed a few bugs too.
Download at the usual location, or SVN update the trunk.
https://sourceforge.net/projects/mosesdecoder/
This is probably the la
make sure the scores of the unknown word (-100) is included in your
calculation of future cost.
On 09/08/2010 08:02, nghi...@comp.nus.edu.sg wrote:
> Hi everyone,
>
> I would like to ask for some details on how Moses deals with the handling
> of unknown words. As I read from the tutorial, unkno
> With the default setting of Moses (phrase-based, distance-based reordering
> ...), the handling of unknown words will be postponed (as we penalize them
> severely : -100) until the very end.
>
> Therefore, it is likely that some unknown words are dropped and won't
> appear in the output (due to
Hi everyone,
I would like to ask for some details on how Moses deals with the handling
of unknown words. As I read from the tutorial, unknown words are copied
verbatim to the output. However, it is not clear of how we deal with the
distortion limit while copying unknown words to the output.
The s
15 matches
Mail list logo
