>
> Dear all,
>
> We have an opening for a 3-year position of Research Associate or Research
> Fellow in Machine Learning with applications to Machine Translation and
> Multimodal Language Processing. This position is funded by the ERC MultiMT
> project: Multi-modal Context Modelling for Machine Tr
Hi,
I am not sure what you mean by the best "phrase segmentation" - according
to what criteria?
If you run Moses with the "-t" it will give you the phrase segmentation and
its phrase/word alignment
for the best translation.
If you already have a translation, then you can use constraint decoding
No,
I want to know if I give in input a source sentence (s) and any translation (t)
of s (in the best case the reference), can MOSES (or another algorithm) give me
in output the best phrase segmentation and alignment between s and t !?
Of course , using the Translation Table used in decoding.
Hi
Could you clarify what you mean by your question?
Are you asking about the phrase segmentation that the decoder used to
produce the best translation? You can get that with the switch "-t".
-phi
On Jul 14, 2016 9:29 AM, "Ameur Douib" wrote:
> Hello moses team,
>
>
> We know that Moses use a
Hi
The step by step instructions vary slightly from the EMS defaults.
To run the pipeline of EMS in a step by step fashion, just look at all the
step files and execute the steps by hand.
This also allows you to see the point of divergence. Note that there is
some randomness in tuning.
-phi
On
Hi Irene,
I think you can just proceed with the steps described in "Corpus
Preparation" and "Language Model Training".
Once you get to "Training the Translation System" you will see the full
set of required parameters for the train-model.perl script, where you
have to set "-external-bin-dir" to
