Hi,
Sounds reasonable to me, but it would be good to have this as an option, as
Miles suggested.
-phi
On 25 Oct 2010 17:40, "Ben Gottesman" wrote:
> Hi,
>
> Are truecase models still widely in use?
>
> I have a proposal for a tweak to the train-truecaser.perl script.
>
> Currently, we don't tak
this sounds risky to me. it would be better to allow the user to
specify the behaviour; for your suggestions, you would add an extra
flag which would enable this. the default would be for truecasing to
operate as it used to.
Miles
On 25 October 2010 17:37, Ben Gottesman wrote:
> Hi,
>
> Are t
Hi,
Are truecase models still widely in use?
I have a proposal for a tweak to the train-truecaser.perl script.
Currently, we don't take the first token of a sentence as evidence for the
true casing of that type, on the basis that the first word of a sentence is
always capitalized. The first tok
Hi,
I added the training script and some documentation:
http://www.statmt.org/mosesdev/?n=Moses.AdvancedFeatures#ntoc25
Let me know, if this actually works.
-phi
On Mon, Oct 25, 2010 at 1:15 PM, Ondrej Bojar wrote:
> Hi, Philipp,
>
> I was wondering what that secret model was... Is there any b
Hi,
not a bug, but a feature:
TDA Members doing business with Moses
The translation industry is steadily appropriating the Moses
translation engine, an open source system available as a kit on the
web. At the TAUS User Conference 2010 in Portland (Oregon) TDA members
from major corporations and
Hi, Philipp,
I was wondering what that secret model was... Is there any brief
documentation of what the Moses code expects to load for this model?
The training of this discriminative word lexicon can be heavily
parallelized. Is there any such implementation available, despite not
being efficient
i implemented this years ago (the idea then was to see if for
free-word-order languages, phrases could be generalised). at the time
it didn't seem that there was a more efficient way to do it than just
generate permutations and score them.
and if you think about it, this is essentially the reorde
Hi,
I am not familiar with that, but somewhat related is
Arne Mauser's global lexical model, which also exists
as a secret feature in Moses (secret because no
effiencient training exists):
Citation:
A. Mauser, S. Hasan, and H. Ney. Extending Statistical Machine
Translation with Discriminative and
Hi,
the NULL token is an implicit concept of word alignment
(and it not placed at any specific position). You can see
it popping up in the the lexical translation tables, but
otherwise it is invisible.
-phi
On Mon, Oct 25, 2010 at 11:45 AM, Somayeh Bakhshaei
wrote:
> Hello,
>
> In the theory we
Hello,
In the theory we learn that the null token is place in the beginning of
each sentence. But in the output file of a real system it is seem there
is not such a token implicitly.
--
Best Regards,
S.Bakhshaei
___
Moses-sup
10 matches
Mail list logo
