Moses interprets the string *EPS* as an epsilon transition in the
lattice, which means it can take the transition (and use any
associated features), but the translation model will ignore the
transition.
-Chris

On Fri, Aug 6, 2010 at 11:02 AM, Sylvain Raybaud
<[email protected]> wrote:
> There may be others but I see at least one serious problem: deleting the lincs
> carrying noise information (++noise++) breaks the lattice. I see two
> workarounds:
>
>  1) if (x,y) is such a link, then for each node z such that there exists a
> link (y,z), create a link (x,z) with the same attributes. Then, remove link
> (x,y)
>
>  2) tell moses that it can go through these links but that language and
> translation models should ignore them. Do you know if it's possible?
> Similarly I can tell SRILM to ignore these noises (by creating the LM with -
> non-event option), do you know if the same is possible with giza++?
>
> regards,
>
> On Friday 06 August 2010 15:17:06 Sylvain Raybaud wrote:
>> fixed one more bug. But now... moses just seems to be doing nothing:
>>
>> sylv...@markov /global/markov/raybauds/XP/S2T $ nice moses -inputtype 2 -
>> weight-i 1 -f working-dir/filtered-OlliRehn-1/moses.ini < realworld.plf >
>> out Defined parameters (per moses.ini or switch):
>>         config: working-dir/filtered-OlliRehn-1/moses.ini
>>         distortion-file: 0-0 msd-bidirectional-fe 6
>> /global/markov/raybauds/XP/S2T/working-dir/filtered-OlliRehn-1/reordering-t
>> able distortion-limit: 6
>>         input-factors: 0
>>         inputtype: 2
>>         lmodel-file: 0 0 5
>> /home/sylvain/softs/moses/working-dir/lm/europarl.lm mapping: 0 T 0
>>         ttable-file: 0 0 5
>> /global/markov/raybauds/XP/S2T/working-dir/filtered-
>> OlliRehn-1/phrase-table
>>         ttable-limit: 20
>>         weight-d: 0.054012 0.196064 -0.003181 0.081071 0.086735 0.062332
>> 0.090617
>>         weight-i: 1
>>         weight-l: 0.064254
>>         weight-t: 0.013876 0.081935 0.059305 0.013773 0.145934
>>         weight-w: 0.046909
>> Loading lexical distortion models...
>> have 1 models
>> Creating lexical reordering...
>> weights: 0.196 -0.003 0.081 0.087 0.062 0.091
>> binary file loaded, default OFF_T: -1
>> Created lexical orientation reordering
>> Start loading LanguageModel /home/sylvain/softs/moses/working-
>> dir/lm/europarl.lm : [0.000] seconds
>> Finished loading LanguageModels : [12.000] seconds
>> specified equal numbers of link parameters and insertion weights, not using
>> non-epsilon 'real' word link count.
>> Start loading PhraseTable
>> /global/markov/raybauds/XP/S2T/working-dir/filtered-
>> OlliRehn-1/phrase-table : [12.000] seconds
>> filePath:
>> /global/markov/raybauds/XP/S2T/working-dir/filtered-OlliRehn-1/phrase-
>> table
>> using binary phrase tables for idx 0
>> reading bin ttable
>> size of OFF_T 8
>> binary phrasefile loaded, default OFF_T: -1
>> Finished loading phrase tables : [12.000] seconds
>> IO from STDOUT/STDIN
>> Created input-output object : [12.000] seconds
>> End. : [12.000] seconds
>> confusion net statistics:
>>  created:       1
>>  destroyed:     1
>>  succ. read:    0
>>  columns:       0
>>  words: 0
>>  avg. word/column:      -nan
>>  avg. cols/sent:        -nan
>>
>> On Friday 06 August 2010 15:04:59 Sylvain Raybaud wrote:
>> > Yep that works, I promise next time I'll think before I post :)
>> > Thank you!
>> >
>> > see new script attached.
>> >
>> > On Friday 06 August 2010 14:54:41 Jie Jiang wrote:
>> > > add a \ before that quote
>> > >
>> > > Best regards!
>> > >
>> > > Jie Jiang
>> > > CNGL, School of Computing,
>> > > Dublin City University,
>> > > Glasnevin, Dublin 9.
>> > > Tel: +353 (0)1 700 6724
>> > >
>> > >
>> > >
>> > >
>> > > 2010/8/6 Sylvain Raybaud <[email protected]>
>> > >
>> > > > On Friday 06 August 2010 14:06:55 Sylvain Raybaud wrote:
>> > > > >   * moses cannot translate "real world" graph generated with this
>> > > > >   tool.
>> > > > >
>> > > > > See for example: http://perso.crans.org/raybaud/realworld.slf.gz
>> > > >
>> > > > got it: sphinx hypothesis contains a quote:
>> > > >
>> > > > nous incombe d' assurer
>> > > >
>> > > > which ends up like this in plf:
>> > > >
>> > > > ('d'',x,y)
>> > > >
>> > > > see example7 attached (with quote) and example7.cleaned (no quote):
>> > > > the former
>> > > > gives me the same error, the later is translated just fine.
>> > > >
>> > > >
>> > > > how are we supposed to deal with quotes in PLF?
>> > > >
>> > > > regards,
>> > > >
>> > > > --
>> > > > Sylvain
>> > > >
>> > > > _______________________________________________
>> > > > Moses-support mailing list
>> > > > [email protected]
>> > > > http://mailman.mit.edu/mailman/listinfo/moses-support
>
> --
> Sylvain
> _______________________________________________
> 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