I'm not quite sure why and I'm not sure if multiple translation systems is maintained by anyone.
Is it possible for you not to use multiple translation systems? I'm thinking of getting rid of it soon because it makes the code quite complicated On 9 January 2013 18:20, Fong Po Po <[email protected]> wrote: > Dear all: > > I can use Mosesserver to run multiple translation systems with > language model srilm. > But I cannot use Mosesserver to to this with kenLM. > I have created binary file of language model, phrase-table and > reorder-table. > I run mosesserver like this: > ./mosesserver -f moses.ini --server-port 9083 > And client inputs sentence: > utilização e > and choose translation system: pc > > The output screen of mosesserver like this: > ............ > .............. > Input: utilização e > exploração > > Using translation system pc > Translating: utilização e exploração > reading bin ttable > size of OFF_T 8 > binary phrasefile loaded, default OFF_T: -1 > binary file loaded, default OFF_T: -1 > Translation system not found default > > Moses Server cannot run multiple translation systems in kenLM, > why? > But it can do this with srilm. > > > > My moses.ini is: > > ######################### > ### MOSES CONFIG FILE ### > ######################### > > # D - decoding path, R - reordering model, L - language model > [translation-systems] > pc D 0 R 0 L 0 > # input factors > [input-factors] > 0 > > # mapping steps > [mapping] > 0 T 0 > # translation tables: table type (hierarchical(0), textual (0), binary > (1)), source-factors, target-factors, number of scores, file > # OLD FORMAT is still handled for back-compatibility > # OLD FORMAT translation tables: source-factors, target-factors, number of > scores, file > # OLD FORMAT a binary table type (1) is assumed > [ttable-file] > 1 0 0 5 > /home/sunnymoon/research/mosesdecoder/scripts/training/model-port-chn-s/phrase-table > # no generation models, no generation-file section > # language models: type(srilm/irstlm), factors, order, file > [lmodel-file] > 8 0 5 > /home/sunnymoon/research/mosesdecoder/scripts/training/model-port-chn-s/sample.binary > > # limit on how many phrase translations e for each phrase f are loaded > # 0 = all elements loaded > [ttable-limit] > 20 > > # distortion (reordering) files > [distortion-file] > 0-0 wbe-msd-bidirectional-fe-allff 6 > /home/sunnymoon/research/mosesdecoder/scripts/training/model-port-chn-s/reordering-table > > # distortion (reordering) weight > [weight-d] > 0.3 > 0.3 > 0.3 > 0.3 > 0.3 > 0.3 > 0.3 > # language model weights > [weight-l] > 0.5000 > # translation model weights > [weight-t] > 0.20 > 0.20 > 0.20 > 0.20 > 0.20 > > # no generation models, no weight-generation section > # word penalty > [weight-w] > -1 > > [distortion-limit] > 6 > > Can you help me? > Thanks! > > Best Regards, > > Fong Pui Chi > > > > > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > > -- Research Associate University of Edinburgh http://www.hoang.co.uk
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
