Hi, if you do not have a glue grammar, then often no translation can be found with syntax-based models. So, it is highly recommended to have such a grammar.
-phi 2010/5/28 dongxinghua0213 <[email protected]>: > > > > ---------- 转发邮件信息 ---------- > 发件人："dongxinghua0213 <[email protected]>" > 发送日期：2010-05-28 12:50:40 > 收件人："Philipp Koehn" <[email protected]> > 主题： tree-to-string model tuning parameter error > hello, > > I trained tree-to-string model using moses , Should I also add the > options -hierarchical -glue-grammar, or only --source-syntax ,another > problem,when tuning the parametres,an error occurred, like this: > > ........... > > NO BEST TRANSLATION > End. : [34.000] seconds > Peeking at the beginning of nbestlist to get order of scores: > run1.best100.out > Line empty in nbestlist 'run1.best100.out' at > tools/moses-scripts/scripts-20100517-1641/training/mert-moses.pl line 906. > > contents in moses.ini: > ######################### > ### MOSES CONFIG FILE ### > ######################### > # input factors > [input-factors] > 0 > # mapping steps > [mapping] > 0 T 0 > 1 T 1 > # translation tables: source-factors, target-factors, number of scores, file > [ttable-file] > 6 0 0 5 /home/top/programming/language_model/syntax-dir/model/rule-table.gz > # no generation models, no generation-file section > # language models: type(srilm/irstlm), factors, order, file > [lmodel-file] > 0 0 3 /home/top/programming/language_model/syntax-dir/lm/raw.ch.lm > # limit on how many phrase translations e for each phrase f are loaded > # 0 = all elements loaded > [ttable-limit] > 20 > # language model weights > [weight-l] > 0.5000 > # translation model weights > [weight-t] > 0.2 > 0.2 > 0.2 > 0.2 > 0.2 > 1.0 > # no generation models, no weight-generation section > # word penalty > [weight-w] > -1 > [cube-pruning-pop-limit] > 1000 > [glue-rule-type] > 0 > [non-terminals] > X > [search-algorithm] > 3 > [inputtype] > 3 > [max-chart-span] > 20 > 1000 > > > I find in the filtered folder ,phrase table is empty ,I also created > rules.bin to decode ,but failed ,too! > Is the parallel corpus too small ? It's only 4000 lines. > best wishes ! > > > ________________________________ > 网易为中小企业免费提供企业邮箱（自主域名） > > ________________________________ > 网易为中小企业免费提供企业邮箱（自主域名） > _______________________________________________ > 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
