Hello,
You can also have a look at force alignment using mgiza++ for aligning
additional documents without retraining ( if you have previous
training models saved.)
Regards,
Amit
On Wednesday, January 12, 2011, Sébastien Druon
wrote:
> Hello,
> Is it possible to train moses incrementally?
> As
It works, thank you !
On Tuesday 11 January 2011 20:46:04 Kenneth Heafield wrote:
> I've just checked in revision 3796 which fixes this problem, including
> the OnDiskWrapper issue for bonus kicks.
>
> Tested with: ./configure, ./configure --without-kenlm, ./configure
> --enable-shared, and ./con
sorry, the code is not publically available yet. we will probably
release it in the near future
Miles
On 12 January 2011 09:36, Sébastien Druon wrote:
> Thanks for this answer...
> Is there some code available?
> When will it be integrated into Moses?
> Thanks again
> Sebastien
>
> On 12 Jan 20
Thanks for this answer...
Is there some code available?
When will it be integrated into Moses?
Thanks again
Sebastien
On 12 Jan 2011 09:21, "Miles Osborne" wrote:
yes. we have done this for both Giza++ and for the language model:
Stream-based Translation Models for Statistical Machine Translat
yes. we have done this for both Giza++ and for the language model:
Stream-based Translation Models for Statistical Machine Translation,
Abby Levenberg, Chris Callison-Burch and Miles Osborne, NAACL 2010
Stream-based Randomised Language Models for SMT, Abby Levenberg and
Miles Osborne, EMNLP 2009
Hello,
Is it possible to train moses incrementally?
As I understood the standard behaviour is to take a whole bunch of documents
and train moses on it all.
Is there a possibility for example to add new documents afterwards without
retraining everything?
Thanks in advance
Sebastien
___
