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 <sylvain.rayb...@loria.fr> > > > > > > > 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 > > > > Moses-support@mit.edu > > > > http://mailman.mit.edu/mailman/listinfo/moses-support -- Sylvain _______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
