This could have to do with the language interpolation mechanics, which
'deletes' LMs from the moses.ini and makes them part of the
interpolation instead. Does adding
exclude-from-interpolation = true
help?
Alternatively: the LM should still have its own section, [LM:somename],
and you should set order, factor etc. correctly.
best wishes,
Rico
On 19/06/15 20:19, Lane Schwartz wrote:
Hrm.. that's exactly what I had tried to do. It complained with the
following error:
ERROR: use --lm factor:order:filename to specify at least one language
model at /opt/moses/scripts/training/train-model.perl line 479
On Fri, Jun 19, 2015 at 2:17 PM, Rico Sennrich <[email protected]
<mailto:[email protected]>> wrote:
Lane Schwartz <dowobeha@...> writes:
>
> Hi,
>
> I've looked through experiment.meta and the samples, and I
haven't been
able to figure this out. I know this is simple, but I'm missing
the syntax.
>
> How can I tell EMS to use an existing binarized LM that was trained
previously?
>
> Thanks,
> Lane
>
Hi Lane,
instead of
raw-corpus = /path/to/corpus
use
binlm = /path/to/lm
_______________________________________________
Moses-support mailing list
[email protected] <mailto:[email protected]>
http://mailman.mit.edu/mailman/listinfo/moses-support
--
When a place gets crowded enough to require ID's, social collapse is not
far away. It is time to go elsewhere. The best thing about space travel
is that it made it possible to go elsewhere.
-- R.A. Heinlein, "Time Enough For Love"
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
