Hey I just did that, comparing the reordering tables... changed the 2 to a 4
in the moses.ini and added 2 distortion weights, thanks!

Sorry I replied before checking, I just didnt understand why I had to do
that, thanks a lot! :)

2010/3/20 maria sol ferrer <[email protected]>

> hey thanks for your answers.. let's see if i got this right.. I trained
> with -monotonicity-bidirectional-fe, the training went fine (the problem is
> translating, as I mentioned before) and here is some extracts of the
> generated files:
>
> reordering-table:
> " ( from ||| " ( del ||| 0.6 0.4 0.6 0.4
> " ( generative components ) , ||| " ( componentes de generación ) , ||| 0.6
> 0.4 0.6 0.4
> " ( generative components ) ||| " ( componentes de generación ) ||| 0.6 0.4
> 0.6 0.4
>
> extract.o
> a ||| una ||| mono other
> a production plant for ||| una planta de producción ||| mono other
> a production plant for ||| una planta de producción de ||| mono other
>
> moses.ini
> # distortion (reordering) files
> [distortion-file]
> 0-0 monotonicity-bidirectional-fe 2
> /home/puchi/redsea/work_mono-bi-fe/work/model/reordering-table.gz
> # distortion (reordering) weight
> [weight-d]
> 0.3
> 0.3
> 0.3
>
> now that's what the training generated, i didnt change anything. So what ur
> saying is that the 2 in the moses.ini should be a 4? because there are 4
> weights in the reordering table?..
>
> Then why does it generate the wrong numbers if it worked fine for de msd
> model?
>
> thanks!
>
> 2010/3/20 Sara Stymne <[email protected]>
>
> Hi Maria!
>>
>> The model msd-bidirectional-e will not work, since you can only
>> condition lexical reordering models on either the foreign phrase (f) or
>> both the foreign and the target (fe). Only on the target (e) is not
>> supported.
>>
>> There is actually an error on the Moses webpage
>> (http://www.statmt.org/moses/?n=FactoredTraining.BuildReorderingModel),
>> where it says that this e-model is acceptable.
>>
>> If you want to train unidirectional models, you should not use
>> -unidirectional in your command for the training script, it is chosen by
>> default. So change your second model to: msd-fe, at training time.
>>
>> At decoding time: if you're using a monotonicity model, make sure that
>> the number of weights specified in the moses.ini file, actually are the
>> same as in the reordering table.
>>
>> /Sara
>>
>>
>> 2010-03-18 21:57, maria sol ferrer skrev:
>> > Hey, thanks for your help.
>> >
>> > Does anyone else know what might be wrong with changing the reordering
>> > model? has anyone done it successfully? I really cant get it working and
>> > there's no help on the web.
>> >
>> > Thanks a lot.
>> >
>> > 2010/3/19 Hieu Hoang <[email protected] <mailto:[email protected]>>
>> >
>> >     i can't see any obvious problems.
>> >
>> >     i don't know much about the lexicalized reordering. It seems like
>> >     the number of scores is not what is expected by the decoder for the
>> >     particular setting specified in the ini file. I think in training,
>> >     you have to specify what type of reordering model you want, and
>> >     specify the SAME type when decoding.
>> >
>> >     sorry i can't be of more help
>> >
>> >
>> >     On 17 March 2010 21:35, maria sol ferrer <[email protected]
>> >     <mailto:[email protected]>> wrote:
>> >
>> >         Hey, thanks for your answer, here is the ini file and the output
>> >         from when i try to translate...
>> >
>> >         2010/3/18 Hieu Hoang <[email protected]
>> >         <mailto:[email protected]>>
>> >
>> >             can you send me the ini file, i'll try & see if there's
>> >             anything obviously wrong
>> >
>> >
>> >             On 17/03/2010 05:09, maria sol ferrer wrote:
>> >>             Hi, I was running some tests on different reordering types
>> >>             and when I tried with
>> >>
>> >>             msd-bidirectional-e, msd-unidirectional-fe and
>> >>             monotonicity-bidirectional-fe
>> >>
>> >>             the first 2 gave the error that reordering doesnt exist
>> >>             during training, the third trained fine but when trying to
>> >>             translate, it didnt, the only message there was was:
>> >>             Reordering types NOT individualy weighted! (By the way,
>> >>             the default reordering works fine)
>> >>
>> >>             I searched the web and all I found was another question on
>> >>             the mailing list like this, about the monotonicity
>> >>             reordering (all of them) not working, but it was never
>> >>             answered.
>> >>
>> >>             I'm running an english-spanish decoder and the reordering
>> >>             is not so good, it just pretty much translates in the
>> >>             english order, which is not always correct in spanish.
>> >>
>> >>             I'd apreciate your help, thanks.
>> >>
>> >>
>> >>             _______________________________________________
>> >>             Moses-support mailing list
>> >>             [email protected]  <mailto:[email protected]>
>> >>             http://mailman.mit.edu/mailman/listinfo/moses-support
>> >>
>> >
>> >
>> >
>> >
>> >
>> >
>> > _______________________________________________
>> > Moses-support mailing list
>> > [email protected]
>> > http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>> _______________________________________________
>> Moses-support mailing list
>> [email protected]
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>
>
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to